► 代码示例 / 结构化数据 / 使用 Wide、Deep 和 Cross 网络进行结构化数据学习

使用 Wide、Deep 和 Cross 网络进行结构化数据学习

作者： Khalid Salama
创建日期 2020/12/31
最后修改日期 2025/01/03
描述： 使用 Wide & Deep 和 Deep & Cross 网络进行结构化数据分类。

ⓘ 此示例使用 Keras 3

在 Colab 中查看 • GitHub 源码

引言

本示例演示如何使用以下两种建模技术进行结构化数据分类

Wide & Deep 模型
Deep & Cross 模型

请注意，此示例应使用 TensorFlow 2.5 或更高版本运行。

数据集

本示例使用 UCI 机器学习库中的 Covertype 数据集。任务是从制图变量预测森林覆盖类型。数据集包含 506,011 个样本，具有 12 个输入特征：10 个数值特征和 2 个分类特征。每个样本被分为 7 个类别之一。

设置

import os

# Only the TensorFlow backend supports string inputs.
os.environ["KERAS_BACKEND"] = "tensorflow"

import math
import numpy as np
import pandas as pd
from tensorflow import data as tf_data
import keras
from keras import layers

准备数据

首先，我们将数据集从 UCI 机器学习库加载到 Pandas DataFrame 中

data_url = (
    "https://archive.ics.uci.edu/ml/machine-learning-databases/covtype/covtype.data.gz"
)
raw_data = pd.read_csv(data_url, header=None)
print(f"Dataset shape: {raw_data.shape}")
raw_data.head()

Dataset shape: (581012, 55)

	0	1	2	3	4	5	6	7	8	9	...	54
0	2596	51	3	258	0	510	221	232	148	6279	...	5
1	2590	56	2	212	-6	390	220	235	151	6225	...	5
2	2804	139	9	268	65	3180	234	238	135	6121	...	2
3	2785	155	18	242	118	3090	238	238	122	6211	...	2
4	2595	45	2	153	-1	391	220	234	150	6172	...	5

5 rows × 55 columns

数据集中的两个分类特征是二值编码的。我们将把这种数据集表示转换为典型表示，其中每个分类特征表示为单个整数值。

soil_type_values = [f"soil_type_{idx+1}" for idx in range(40)]
wilderness_area_values = [f"area_type_{idx+1}" for idx in range(4)]

soil_type = raw_data.loc[:, 14:53].apply(
    lambda x: soil_type_values[0::1][x.to_numpy().nonzero()[0][0]], axis=1
)
wilderness_area = raw_data.loc[:, 10:13].apply(
    lambda x: wilderness_area_values[0::1][x.to_numpy().nonzero()[0][0]], axis=1
)

CSV_HEADER = [
    "Elevation",
    "Aspect",
    "Slope",
    "Horizontal_Distance_To_Hydrology",
    "Vertical_Distance_To_Hydrology",
    "Horizontal_Distance_To_Roadways",
    "Hillshade_9am",
    "Hillshade_Noon",
    "Hillshade_3pm",
    "Horizontal_Distance_To_Fire_Points",
    "Wilderness_Area",
    "Soil_Type",
    "Cover_Type",
]

data = pd.concat(
    [raw_data.loc[:, 0:9], wilderness_area, soil_type, raw_data.loc[:, 54]],
    axis=1,
    ignore_index=True,
)
data.columns = CSV_HEADER

# Convert the target label indices into a range from 0 to 6 (there are 7 labels in total).
data["Cover_Type"] = data["Cover_Type"] - 1

print(f"Dataset shape: {data.shape}")
data.head().T

Dataset shape: (581012, 13)

	0	1	2	3	4
海拔	2596	2590	2804	2785	2595
坡向	51	56	139	155	45
坡度	3	2	9	18	2
水平距水源距离	258	212	268	242	153
垂直距水源距离	0	-6	65	118	-1
水平距公路距离	510	390	3180	3090	391
早上9点山体阴影	221	220	234	238	220
正午山体阴影	232	235	238	238	234
下午3点山体阴影	148	151	135	122	150
水平距火点距离	6279	6225	6121	6211	6172
荒野区	区域类型 1	区域类型 1	区域类型 1	区域类型 1	区域类型 1
土壤类型	土壤类型 29	土壤类型 29	土壤类型 12	土壤类型 30	土壤类型 29
覆盖类型	4	4	1	1	4

DataFrame 的形状显示每个样本有 13 列（12 列用于特征，1 列用于目标标签）。

我们将数据分割成训练集（85%）和测试集（15%）。

train_splits = []
test_splits = []

for _, group_data in data.groupby("Cover_Type"):
    random_selection = np.random.rand(len(group_data.index)) <= 0.85
    train_splits.append(group_data[random_selection])
    test_splits.append(group_data[~random_selection])

train_data = pd.concat(train_splits).sample(frac=1).reset_index(drop=True)
test_data = pd.concat(test_splits).sample(frac=1).reset_index(drop=True)

print(f"Train split size: {len(train_data.index)}")
print(f"Test split size: {len(test_data.index)}")

Train split size: 494149
Test split size: 86863

接下来，将训练数据和测试数据存储在单独的 CSV 文件中。

train_data_file = "train_data.csv"
test_data_file = "test_data.csv"

train_data.to_csv(train_data_file, index=False)
test_data.to_csv(test_data_file, index=False)

定义数据集元数据

在此，我们定义数据集的元数据，这将有助于读取和解析数据为输入特征，并根据它们的类型编码输入特征。

TARGET_FEATURE_NAME = "Cover_Type"

TARGET_FEATURE_LABELS = ["0", "1", "2", "3", "4", "5", "6"]

NUMERIC_FEATURE_NAMES = [
    "Aspect",
    "Elevation",
    "Hillshade_3pm",
    "Hillshade_9am",
    "Hillshade_Noon",
    "Horizontal_Distance_To_Fire_Points",
    "Horizontal_Distance_To_Hydrology",
    "Horizontal_Distance_To_Roadways",
    "Slope",
    "Vertical_Distance_To_Hydrology",
]

CATEGORICAL_FEATURES_WITH_VOCABULARY = {
    "Soil_Type": list(data["Soil_Type"].unique()),
    "Wilderness_Area": list(data["Wilderness_Area"].unique()),
}

CATEGORICAL_FEATURE_NAMES = list(CATEGORICAL_FEATURES_WITH_VOCABULARY.keys())

FEATURE_NAMES = NUMERIC_FEATURE_NAMES + CATEGORICAL_FEATURE_NAMES

COLUMN_DEFAULTS = [
    [0] if feature_name in NUMERIC_FEATURE_NAMES + [TARGET_FEATURE_NAME] else ["NA"]
    for feature_name in CSV_HEADER
]

NUM_CLASSES = len(TARGET_FEATURE_LABELS)

实验设置

接下来，我们定义一个输入函数，该函数读取并解析文件，然后将特征和标签转换为用于训练或评估的tf.data.Dataset。

# To convert the datasets elements to from OrderedDict to Dictionary
def process(features, target):
    return dict(features), target


def get_dataset_from_csv(csv_file_path, batch_size, shuffle=False):
    dataset = tf_data.experimental.make_csv_dataset(
        csv_file_path,
        batch_size=batch_size,
        column_names=CSV_HEADER,
        column_defaults=COLUMN_DEFAULTS,
        label_name=TARGET_FEATURE_NAME,
        num_epochs=1,
        header=True,
        shuffle=shuffle,
    ).map(process)
    return dataset.cache()

在此，我们配置给定模型的参数并实现运行训练和评估实验的步骤。

learning_rate = 0.001
dropout_rate = 0.1
batch_size = 265
num_epochs = 1

hidden_units = [32, 32]


def run_experiment(model):
    model.compile(
        optimizer=keras.optimizers.Adam(learning_rate=learning_rate),
        loss=keras.losses.SparseCategoricalCrossentropy(),
        metrics=[keras.metrics.SparseCategoricalAccuracy()],
    )

    train_dataset = get_dataset_from_csv(train_data_file, batch_size, shuffle=True)

    test_dataset = get_dataset_from_csv(test_data_file, batch_size)

    print("Start training the model...")
    history = model.fit(train_dataset, epochs=num_epochs)
    print("Model training finished")

    _, accuracy = model.evaluate(test_dataset, verbose=0)

    print(f"Test accuracy: {round(accuracy * 100, 2)}%")

创建模型输入

现在，将模型的输入定义为一个字典，其中键是特征名称，值是一个具有相应特征形状和数据类型的 keras.layers.Input 张量。

def create_model_inputs():
    inputs = {}
    for feature_name in FEATURE_NAMES:
        if feature_name in NUMERIC_FEATURE_NAMES:
            inputs[feature_name] = layers.Input(
                name=feature_name, shape=(), dtype="float32"
            )
        else:
            inputs[feature_name] = layers.Input(
                name=feature_name, shape=(), dtype="string"
            )
    return inputs

编码特征

我们创建输入特征的两种表示：稀疏表示和密集表示： 1. 在稀疏表示中，使用 CategoryEncoding 层对分类特征进行独热编码。这种表示对于模型记忆特定特征值以进行某些预测非常有用。 2. 在密集表示中，使用 Embedding 层对分类特征进行低维嵌入编码。这种表示有助于模型很好地泛化到未见的特征组合。

def encode_inputs(inputs, use_embedding=False):
    encoded_features = []
    for feature_name in inputs:
        if feature_name in CATEGORICAL_FEATURE_NAMES:
            vocabulary = CATEGORICAL_FEATURES_WITH_VOCABULARY[feature_name]
            # Create a lookup to convert string values to an integer indices.
            # Since we are not using a mask token nor expecting any out of vocabulary
            # (oov) token, we set mask_token to None and  num_oov_indices to 0.
            lookup = layers.StringLookup(
                vocabulary=vocabulary,
                mask_token=None,
                num_oov_indices=0,
                output_mode="int" if use_embedding else "binary",
            )
            if use_embedding:
                # Convert the string input values into integer indices.
                encoded_feature = lookup(inputs[feature_name])
                embedding_dims = int(math.sqrt(len(vocabulary)))
                # Create an embedding layer with the specified dimensions.
                embedding = layers.Embedding(
                    input_dim=len(vocabulary), output_dim=embedding_dims
                )
                # Convert the index values to embedding representations.
                encoded_feature = embedding(encoded_feature)
            else:
                # Convert the string input values into a one hot encoding.
                encoded_feature = lookup(
                    keras.ops.expand_dims(inputs[feature_name], -1)
                )
        else:
            # Use the numerical features as-is.
            encoded_feature = keras.ops.expand_dims(inputs[feature_name], -1)

        encoded_features.append(encoded_feature)

    all_features = layers.concatenate(encoded_features)
    return all_features

实验 1：一个基准模型

在第一个实验中，我们创建一个多层前馈网络，其中分类特征采用独热编码。

def create_baseline_model():
    inputs = create_model_inputs()
    features = encode_inputs(inputs)

    for units in hidden_units:
        features = layers.Dense(units)(features)
        features = layers.BatchNormalization()(features)
        features = layers.ReLU()(features)
        features = layers.Dropout(dropout_rate)(features)

    outputs = layers.Dense(units=NUM_CLASSES, activation="softmax")(features)
    model = keras.Model(inputs=inputs, outputs=outputs)
    return model


baseline_model = create_baseline_model()
keras.utils.plot_model(baseline_model, show_shapes=True, rankdir="LR")

png

运行它

run_experiment(baseline_model)

Start training the model...

  1/Unknown  6s 6s/step - loss: 2.2346 - sparse_categorical_accuracy: 0.1472


  2/Unknown  6s 263ms/step - loss: 2.2343 - sparse_categorical_accuracy: 0.1519


  3/Unknown  6s 267ms/step - loss: 2.2241 - sparse_categorical_accuracy: 0.1549


  4/Unknown  7s 256ms/step - loss: 2.2228 - sparse_categorical_accuracy: 0.1544


  5/Unknown  7s 256ms/step - loss: 2.2205 - sparse_categorical_accuracy: 0.1546


  6/Unknown  7s 253ms/step - loss: 2.2183 - sparse_categorical_accuracy: 0.1556


  7/Unknown  7s 250ms/step - loss: 2.2135 - sparse_categorical_accuracy: 0.1571


  8/Unknown  8s 247ms/step - loss: 2.2093 - sparse_categorical_accuracy: 0.1584


  9/Unknown  8s 242ms/step - loss: 2.2049 - sparse_categorical_accuracy: 0.1596


 10/Unknown  8s 238ms/step - loss: 2.2003 - sparse_categorical_accuracy: 0.1610


 11/Unknown  8s 236ms/step - loss: 2.1958 - sparse_categorical_accuracy: 0.1626


 12/Unknown  8s 235ms/step - loss: 2.1911 - sparse_categorical_accuracy: 0.1641


 13/Unknown  9s 231ms/step - loss: 2.1862 - sparse_categorical_accuracy: 0.1657


 14/Unknown  9s 228ms/step - loss: 2.1811 - sparse_categorical_accuracy: 0.1676


 15/Unknown  9s 224ms/step - loss: 2.1761 - sparse_categorical_accuracy: 0.1694


 16/Unknown  9s 222ms/step - loss: 2.1707 - sparse_categorical_accuracy: 0.1713


 17/Unknown  9s 220ms/step - loss: 2.1650 - sparse_categorical_accuracy: 0.1734


 18/Unknown  10s 219ms/step - loss: 2.1592 - sparse_categorical_accuracy: 0.1754


 19/Unknown  10s 218ms/step - loss: 2.1535 - sparse_categorical_accuracy: 0.1773


 20/Unknown  10s 218ms/step - loss: 2.1476 - sparse_categorical_accuracy: 0.1792


 21/Unknown  10s 218ms/step - loss: 2.1416 - sparse_categorical_accuracy: 0.1812


 22/Unknown  10s 218ms/step - loss: 2.1355 - sparse_categorical_accuracy: 0.1834


 23/Unknown  11s 218ms/step - loss: 2.1295 - sparse_categorical_accuracy: 0.1855


 24/Unknown  11s 219ms/step - loss: 2.1235 - sparse_categorical_accuracy: 0.1876


 25/Unknown  11s 219ms/step - loss: 2.1174 - sparse_categorical_accuracy: 0.1897


 26/Unknown  11s 219ms/step - loss: 2.1114 - sparse_categorical_accuracy: 0.1918


 27/Unknown  12s 219ms/step - loss: 2.1054 - sparse_categorical_accuracy: 0.1940


 28/Unknown  12s 218ms/step - loss: 2.0995 - sparse_categorical_accuracy: 0.1961


 29/Unknown  12s 218ms/step - loss: 2.0936 - sparse_categorical_accuracy: 0.1982


 30/Unknown  12s 219ms/step - loss: 2.0878 - sparse_categorical_accuracy: 0.2004


 31/Unknown  12s 219ms/step - loss: 2.0819 - sparse_categorical_accuracy: 0.2026


 32/Unknown  13s 219ms/step - loss: 2.0761 - sparse_categorical_accuracy: 0.2049


 33/Unknown  13s 219ms/step - loss: 2.0703 - sparse_categorical_accuracy: 0.2071


 34/Unknown  13s 220ms/step - loss: 2.0645 - sparse_categorical_accuracy: 0.2094


 35/Unknown  13s 220ms/step - loss: 2.0588 - sparse_categorical_accuracy: 0.2117


 36/Unknown  14s 220ms/step - loss: 2.0531 - sparse_categorical_accuracy: 0.2140


 37/Unknown  14s 221ms/step - loss: 2.0475 - sparse_categorical_accuracy: 0.2163


 38/Unknown  14s 220ms/step - loss: 2.0419 - sparse_categorical_accuracy: 0.2186


 39/Unknown  14s 221ms/step - loss: 2.0364 - sparse_categorical_accuracy: 0.2209


 40/Unknown  14s 221ms/step - loss: 2.0308 - sparse_categorical_accuracy: 0.2233


 41/Unknown  15s 220ms/step - loss: 2.0252 - sparse_categorical_accuracy: 0.2256


 42/Unknown  15s 221ms/step - loss: 2.0198 - sparse_categorical_accuracy: 0.2280


 43/Unknown  15s 221ms/step - loss: 2.0143 - sparse_categorical_accuracy: 0.2303


 44/Unknown  15s 221ms/step - loss: 2.0089 - sparse_categorical_accuracy: 0.2326


 45/Unknown  16s 221ms/step - loss: 2.0035 - sparse_categorical_accuracy: 0.2348


 46/Unknown  16s 222ms/step - loss: 1.9982 - sparse_categorical_accuracy: 0.2371


 47/Unknown  16s 221ms/step - loss: 1.9929 - sparse_categorical_accuracy: 0.2393


 48/Unknown  16s 221ms/step - loss: 1.9877 - sparse_categorical_accuracy: 0.2416


 49/Unknown  16s 222ms/step - loss: 1.9824 - sparse_categorical_accuracy: 0.2438


 50/Unknown  17s 222ms/step - loss: 1.9773 - sparse_categorical_accuracy: 0.2460


 51/Unknown  17s 223ms/step - loss: 1.9721 - sparse_categorical_accuracy: 0.2481


 52/Unknown  17s 223ms/step - loss: 1.9670 - sparse_categorical_accuracy: 0.2503


 53/Unknown  17s 224ms/step - loss: 1.9620 - sparse_categorical_accuracy: 0.2525


 54/Unknown  18s 224ms/step - loss: 1.9569 - sparse_categorical_accuracy: 0.2546


 55/Unknown  18s 225ms/step - loss: 1.9519 - sparse_categorical_accuracy: 0.2568


 56/Unknown  18s 226ms/step - loss: 1.9470 - sparse_categorical_accuracy: 0.2589


 57/Unknown  18s 226ms/step - loss: 1.9421 - sparse_categorical_accuracy: 0.2610


 58/Unknown  19s 226ms/step - loss: 1.9373 - sparse_categorical_accuracy: 0.2631


 59/Unknown  19s 226ms/step - loss: 1.9324 - sparse_categorical_accuracy: 0.2652


 60/Unknown  19s 226ms/step - loss: 1.9276 - sparse_categorical_accuracy: 0.2673


 61/Unknown  19s 227ms/step - loss: 1.9229 - sparse_categorical_accuracy: 0.2694


 62/Unknown  20s 227ms/step - loss: 1.9182 - sparse_categorical_accuracy: 0.2714


 63/Unknown  20s 227ms/step - loss: 1.9136 - sparse_categorical_accuracy: 0.2734


 64/Unknown  20s 228ms/step - loss: 1.9090 - sparse_categorical_accuracy: 0.2754


 65/Unknown  20s 228ms/step - loss: 1.9044 - sparse_categorical_accuracy: 0.2774


 66/Unknown  21s 229ms/step - loss: 1.8999 - sparse_categorical_accuracy: 0.2794


 67/Unknown  21s 229ms/step - loss: 1.8954 - sparse_categorical_accuracy: 0.2813


 68/Unknown  21s 229ms/step - loss: 1.8910 - sparse_categorical_accuracy: 0.2832


 69/Unknown  21s 229ms/step - loss: 1.8866 - sparse_categorical_accuracy: 0.2852


 70/Unknown  22s 229ms/step - loss: 1.8822 - sparse_categorical_accuracy: 0.2870


 71/Unknown  22s 229ms/step - loss: 1.8779 - sparse_categorical_accuracy: 0.2889


 72/Unknown  22s 230ms/step - loss: 1.8736 - sparse_categorical_accuracy: 0.2908


 73/Unknown  22s 230ms/step - loss: 1.8694 - sparse_categorical_accuracy: 0.2926


 74/Unknown  23s 230ms/step - loss: 1.8652 - sparse_categorical_accuracy: 0.2945


 75/Unknown  23s 230ms/step - loss: 1.8611 - sparse_categorical_accuracy: 0.2963


 76/Unknown  23s 230ms/step - loss: 1.8569 - sparse_categorical_accuracy: 0.2980


 77/Unknown  23s 230ms/step - loss: 1.8529 - sparse_categorical_accuracy: 0.2998


 78/Unknown  23s 229ms/step - loss: 1.8488 - sparse_categorical_accuracy: 0.3015


 79/Unknown  24s 229ms/step - loss: 1.8448 - sparse_categorical_accuracy: 0.3033


 80/Unknown  24s 229ms/step - loss: 1.8408 - sparse_categorical_accuracy: 0.3050


 81/Unknown  24s 228ms/step - loss: 1.8369 - sparse_categorical_accuracy: 0.3067


 82/Unknown  24s 228ms/step - loss: 1.8329 - sparse_categorical_accuracy: 0.3084


 83/Unknown  24s 228ms/step - loss: 1.8290 - sparse_categorical_accuracy: 0.3100


 84/Unknown  25s 227ms/step - loss: 1.8251 - sparse_categorical_accuracy: 0.3117


 85/Unknown  25s 227ms/step - loss: 1.8213 - sparse_categorical_accuracy: 0.3133


 86/Unknown  25s 227ms/step - loss: 1.8175 - sparse_categorical_accuracy: 0.3149


 87/Unknown  25s 227ms/step - loss: 1.8137 - sparse_categorical_accuracy: 0.3165


 88/Unknown  26s 227ms/step - loss: 1.8099 - sparse_categorical_accuracy: 0.3181


 89/Unknown  26s 227ms/step - loss: 1.8062 - sparse_categorical_accuracy: 0.3197


 90/Unknown  26s 226ms/step - loss: 1.8025 - sparse_categorical_accuracy: 0.3213


 91/Unknown  26s 226ms/step - loss: 1.7988 - sparse_categorical_accuracy: 0.3228


 92/Unknown  26s 226ms/step - loss: 1.7952 - sparse_categorical_accuracy: 0.3243


 93/Unknown  27s 226ms/step - loss: 1.7916 - sparse_categorical_accuracy: 0.3258


 94/Unknown  27s 226ms/step - loss: 1.7880 - sparse_categorical_accuracy: 0.3273


 95/Unknown  27s 226ms/step - loss: 1.7845 - sparse_categorical_accuracy: 0.3288


 96/Unknown  27s 226ms/step - loss: 1.7810 - sparse_categorical_accuracy: 0.3303


 97/Unknown  28s 226ms/step - loss: 1.7775 - sparse_categorical_accuracy: 0.3317


 98/Unknown  28s 226ms/step - loss: 1.7741 - sparse_categorical_accuracy: 0.3331


 99/Unknown  28s 227ms/step - loss: 1.7706 - sparse_categorical_accuracy: 0.3345


100/Unknown  28s 227ms/step - loss: 1.7672 - sparse_categorical_accuracy: 0.3359


101/Unknown  29s 227ms/step - loss: 1.7639 - sparse_categorical_accuracy: 0.3373


102/Unknown  29s 228ms/step - loss: 1.7605 - sparse_categorical_accuracy: 0.3387


103/Unknown  29s 228ms/step - loss: 1.7572 - sparse_categorical_accuracy: 0.3401


104/Unknown  29s 228ms/step - loss: 1.7539 - sparse_categorical_accuracy: 0.3414


105/Unknown  30s 228ms/step - loss: 1.7507 - sparse_categorical_accuracy: 0.3428


106/Unknown  30s 229ms/step - loss: 1.7474 - sparse_categorical_accuracy: 0.3441


107/Unknown  30s 228ms/step - loss: 1.7442 - sparse_categorical_accuracy: 0.3454


108/Unknown  30s 228ms/step - loss: 1.7411 - sparse_categorical_accuracy: 0.3467


109/Unknown  30s 228ms/step - loss: 1.7379 - sparse_categorical_accuracy: 0.3480


110/Unknown  31s 228ms/step - loss: 1.7348 - sparse_categorical_accuracy: 0.3493


111/Unknown  31s 228ms/step - loss: 1.7317 - sparse_categorical_accuracy: 0.3505


112/Unknown  31s 228ms/step - loss: 1.7286 - sparse_categorical_accuracy: 0.3518


113/Unknown  31s 228ms/step - loss: 1.7255 - sparse_categorical_accuracy: 0.3530


114/Unknown  32s 228ms/step - loss: 1.7225 - sparse_categorical_accuracy: 0.3543


115/Unknown  32s 228ms/step - loss: 1.7195 - sparse_categorical_accuracy: 0.3555


116/Unknown  32s 228ms/step - loss: 1.7165 - sparse_categorical_accuracy: 0.3567


117/Unknown  32s 229ms/step - loss: 1.7135 - sparse_categorical_accuracy: 0.3579


118/Unknown  33s 229ms/step - loss: 1.7106 - sparse_categorical_accuracy: 0.3591


119/Unknown  33s 229ms/step - loss: 1.7077 - sparse_categorical_accuracy: 0.3602


120/Unknown  33s 229ms/step - loss: 1.7048 - sparse_categorical_accuracy: 0.3614


121/Unknown  33s 230ms/step - loss: 1.7019 - sparse_categorical_accuracy: 0.3626


122/Unknown  34s 229ms/step - loss: 1.6991 - sparse_categorical_accuracy: 0.3637


123/Unknown  34s 229ms/step - loss: 1.6962 - sparse_categorical_accuracy: 0.3648


124/Unknown  34s 229ms/step - loss: 1.6934 - sparse_categorical_accuracy: 0.3660


125/Unknown  34s 229ms/step - loss: 1.6907 - sparse_categorical_accuracy: 0.3671


126/Unknown  34s 229ms/step - loss: 1.6879 - sparse_categorical_accuracy: 0.3682


127/Unknown  35s 229ms/step - loss: 1.6851 - sparse_categorical_accuracy: 0.3693


128/Unknown  35s 229ms/step - loss: 1.6824 - sparse_categorical_accuracy: 0.3704


129/Unknown  35s 229ms/step - loss: 1.6797 - sparse_categorical_accuracy: 0.3715


130/Unknown  35s 228ms/step - loss: 1.6770 - sparse_categorical_accuracy: 0.3725


131/Unknown  35s 228ms/step - loss: 1.6743 - sparse_categorical_accuracy: 0.3736


132/Unknown  36s 228ms/step - loss: 1.6717 - sparse_categorical_accuracy: 0.3746


133/Unknown  36s 227ms/step - loss: 1.6691 - sparse_categorical_accuracy: 0.3757


134/Unknown  36s 227ms/step - loss: 1.6665 - sparse_categorical_accuracy: 0.3767


135/Unknown  36s 227ms/step - loss: 1.6639 - sparse_categorical_accuracy: 0.3777


136/Unknown  36s 227ms/step - loss: 1.6613 - sparse_categorical_accuracy: 0.3788


137/Unknown  37s 227ms/step - loss: 1.6587 - sparse_categorical_accuracy: 0.3798


138/Unknown  37s 227ms/step - loss: 1.6562 - sparse_categorical_accuracy: 0.3808


139/Unknown  37s 227ms/step - loss: 1.6537 - sparse_categorical_accuracy: 0.3818


140/Unknown  37s 227ms/step - loss: 1.6512 - sparse_categorical_accuracy: 0.3828


141/Unknown  38s 227ms/step - loss: 1.6487 - sparse_categorical_accuracy: 0.3837


142/Unknown  38s 227ms/step - loss: 1.6463 - sparse_categorical_accuracy: 0.3847


143/Unknown  38s 227ms/step - loss: 1.6438 - sparse_categorical_accuracy: 0.3857


144/Unknown  38s 227ms/step - loss: 1.6414 - sparse_categorical_accuracy: 0.3866


145/Unknown  39s 227ms/step - loss: 1.6390 - sparse_categorical_accuracy: 0.3876


146/Unknown  39s 227ms/step - loss: 1.6366 - sparse_categorical_accuracy: 0.3885


147/Unknown  39s 227ms/step - loss: 1.6342 - sparse_categorical_accuracy: 0.3894


148/Unknown  39s 227ms/step - loss: 1.6318 - sparse_categorical_accuracy: 0.3904


149/Unknown  39s 228ms/step - loss: 1.6295 - sparse_categorical_accuracy: 0.3913


150/Unknown  40s 228ms/step - loss: 1.6271 - sparse_categorical_accuracy: 0.3922


151/Unknown  40s 228ms/step - loss: 1.6248 - sparse_categorical_accuracy: 0.3931


152/Unknown  40s 228ms/step - loss: 1.6225 - sparse_categorical_accuracy: 0.3940


153/Unknown  40s 228ms/step - loss: 1.6202 - sparse_categorical_accuracy: 0.3949


154/Unknown  41s 228ms/step - loss: 1.6179 - sparse_categorical_accuracy: 0.3958


155/Unknown  41s 228ms/step - loss: 1.6156 - sparse_categorical_accuracy: 0.3967


156/Unknown  41s 228ms/step - loss: 1.6134 - sparse_categorical_accuracy: 0.3975


157/Unknown  41s 229ms/step - loss: 1.6111 - sparse_categorical_accuracy: 0.3984


158/Unknown  42s 229ms/step - loss: 1.6089 - sparse_categorical_accuracy: 0.3993


159/Unknown  42s 229ms/step - loss: 1.6067 - sparse_categorical_accuracy: 0.4001


160/Unknown  42s 229ms/step - loss: 1.6045 - sparse_categorical_accuracy: 0.4010


161/Unknown  42s 229ms/step - loss: 1.6023 - sparse_categorical_accuracy: 0.4018


162/Unknown  43s 229ms/step - loss: 1.6002 - sparse_categorical_accuracy: 0.4027


163/Unknown  43s 229ms/step - loss: 1.5980 - sparse_categorical_accuracy: 0.4035


164/Unknown  43s 229ms/step - loss: 1.5959 - sparse_categorical_accuracy: 0.4043


165/Unknown  43s 229ms/step - loss: 1.5938 - sparse_categorical_accuracy: 0.4051


166/Unknown  44s 230ms/step - loss: 1.5916 - sparse_categorical_accuracy: 0.4060


167/Unknown  44s 230ms/step - loss: 1.5895 - sparse_categorical_accuracy: 0.4068


168/Unknown  44s 230ms/step - loss: 1.5875 - sparse_categorical_accuracy: 0.4076


169/Unknown  44s 230ms/step - loss: 1.5854 - sparse_categorical_accuracy: 0.4084


170/Unknown  45s 230ms/step - loss: 1.5833 - sparse_categorical_accuracy: 0.4092


171/Unknown  45s 230ms/step - loss: 1.5813 - sparse_categorical_accuracy: 0.4099


172/Unknown  45s 230ms/step - loss: 1.5792 - sparse_categorical_accuracy: 0.4107


173/Unknown  45s 230ms/step - loss: 1.5772 - sparse_categorical_accuracy: 0.4115


174/Unknown  46s 230ms/step - loss: 1.5752 - sparse_categorical_accuracy: 0.4123


175/Unknown  46s 229ms/step - loss: 1.5732 - sparse_categorical_accuracy: 0.4130


176/Unknown  46s 229ms/step - loss: 1.5712 - sparse_categorical_accuracy: 0.4138


177/Unknown  46s 229ms/step - loss: 1.5692 - sparse_categorical_accuracy: 0.4146


178/Unknown  46s 230ms/step - loss: 1.5673 - sparse_categorical_accuracy: 0.4153


179/Unknown  47s 230ms/step - loss: 1.5653 - sparse_categorical_accuracy: 0.4160


180/Unknown  47s 230ms/step - loss: 1.5634 - sparse_categorical_accuracy: 0.4168


181/Unknown  47s 230ms/step - loss: 1.5615 - sparse_categorical_accuracy: 0.4175


182/Unknown  47s 230ms/step - loss: 1.5596 - sparse_categorical_accuracy: 0.4182


183/Unknown  48s 230ms/step - loss: 1.5577 - sparse_categorical_accuracy: 0.4189


184/Unknown  48s 230ms/step - loss: 1.5558 - sparse_categorical_accuracy: 0.4197


185/Unknown  48s 230ms/step - loss: 1.5539 - sparse_categorical_accuracy: 0.4204


186/Unknown  48s 230ms/step - loss: 1.5520 - sparse_categorical_accuracy: 0.4211


187/Unknown  49s 230ms/step - loss: 1.5502 - sparse_categorical_accuracy: 0.4218


188/Unknown  49s 230ms/step - loss: 1.5483 - sparse_categorical_accuracy: 0.4225


189/Unknown  49s 230ms/step - loss: 1.5465 - sparse_categorical_accuracy: 0.4232


190/Unknown  49s 230ms/step - loss: 1.5447 - sparse_categorical_accuracy: 0.4239


191/Unknown  50s 231ms/step - loss: 1.5428 - sparse_categorical_accuracy: 0.4245


192/Unknown  50s 231ms/step - loss: 1.5410 - sparse_categorical_accuracy: 0.4252


193/Unknown  50s 231ms/step - loss: 1.5392 - sparse_categorical_accuracy: 0.4259


194/Unknown  50s 231ms/step - loss: 1.5375 - sparse_categorical_accuracy: 0.4266


195/Unknown  51s 231ms/step - loss: 1.5357 - sparse_categorical_accuracy: 0.4272


196/Unknown  51s 231ms/step - loss: 1.5339 - sparse_categorical_accuracy: 0.4279


197/Unknown  51s 232ms/step - loss: 1.5322 - sparse_categorical_accuracy: 0.4286


198/Unknown  51s 232ms/step - loss: 1.5304 - sparse_categorical_accuracy: 0.4292


199/Unknown  52s 232ms/step - loss: 1.5287 - sparse_categorical_accuracy: 0.4299


200/Unknown  52s 232ms/step - loss: 1.5270 - sparse_categorical_accuracy: 0.4305


201/Unknown  52s 232ms/step - loss: 1.5252 - sparse_categorical_accuracy: 0.4312


202/Unknown  52s 232ms/step - loss: 1.5235 - sparse_categorical_accuracy: 0.4318


203/Unknown  53s 232ms/step - loss: 1.5218 - sparse_categorical_accuracy: 0.4324


204/Unknown  53s 232ms/step - loss: 1.5201 - sparse_categorical_accuracy: 0.4331


205/Unknown  53s 232ms/step - loss: 1.5185 - sparse_categorical_accuracy: 0.4337


206/Unknown  53s 232ms/step - loss: 1.5168 - sparse_categorical_accuracy: 0.4343


207/Unknown  54s 232ms/step - loss: 1.5151 - sparse_categorical_accuracy: 0.4349


208/Unknown  54s 232ms/step - loss: 1.5135 - sparse_categorical_accuracy: 0.4355


209/Unknown  54s 232ms/step - loss: 1.5118 - sparse_categorical_accuracy: 0.4361


210/Unknown  54s 232ms/step - loss: 1.5102 - sparse_categorical_accuracy: 0.4368


211/Unknown  54s 232ms/step - loss: 1.5086 - sparse_categorical_accuracy: 0.4374


212/Unknown  55s 232ms/step - loss: 1.5069 - sparse_categorical_accuracy: 0.4380


213/Unknown  55s 232ms/step - loss: 1.5053 - sparse_categorical_accuracy: 0.4385


214/Unknown  55s 232ms/step - loss: 1.5037 - sparse_categorical_accuracy: 0.4391


215/Unknown  55s 232ms/step - loss: 1.5021 - sparse_categorical_accuracy: 0.4397


216/Unknown  56s 232ms/step - loss: 1.5005 - sparse_categorical_accuracy: 0.4403


217/Unknown  56s 232ms/step - loss: 1.4990 - sparse_categorical_accuracy: 0.4409


218/Unknown  56s 232ms/step - loss: 1.4974 - sparse_categorical_accuracy: 0.4415


219/Unknown  56s 232ms/step - loss: 1.4958 - sparse_categorical_accuracy: 0.4420


220/Unknown  57s 232ms/step - loss: 1.4943 - sparse_categorical_accuracy: 0.4426


221/Unknown  57s 232ms/step - loss: 1.4927 - sparse_categorical_accuracy: 0.4432


222/Unknown  57s 232ms/step - loss: 1.4912 - sparse_categorical_accuracy: 0.4438


223/Unknown  57s 232ms/step - loss: 1.4896 - sparse_categorical_accuracy: 0.4443


224/Unknown  58s 232ms/step - loss: 1.4881 - sparse_categorical_accuracy: 0.4449


225/Unknown  58s 232ms/step - loss: 1.4866 - sparse_categorical_accuracy: 0.4454


226/Unknown  58s 232ms/step - loss: 1.4851 - sparse_categorical_accuracy: 0.4460


227/Unknown  58s 232ms/step - loss: 1.4836 - sparse_categorical_accuracy: 0.4465


228/Unknown  59s 233ms/step - loss: 1.4821 - sparse_categorical_accuracy: 0.4471


229/Unknown  59s 233ms/step - loss: 1.4806 - sparse_categorical_accuracy: 0.4476


230/Unknown  59s 233ms/step - loss: 1.4791 - sparse_categorical_accuracy: 0.4482


231/Unknown  60s 234ms/step - loss: 1.4776 - sparse_categorical_accuracy: 0.4487


232/Unknown  60s 234ms/step - loss: 1.4761 - sparse_categorical_accuracy: 0.4492


233/Unknown  60s 234ms/step - loss: 1.4747 - sparse_categorical_accuracy: 0.4498


234/Unknown  60s 234ms/step - loss: 1.4732 - sparse_categorical_accuracy: 0.4503


235/Unknown  61s 234ms/step - loss: 1.4718 - sparse_categorical_accuracy: 0.4508


236/Unknown  61s 234ms/step - loss: 1.4703 - sparse_categorical_accuracy: 0.4513


237/Unknown  61s 234ms/step - loss: 1.4689 - sparse_categorical_accuracy: 0.4519


238/Unknown  61s 235ms/step - loss: 1.4675 - sparse_categorical_accuracy: 0.4524


239/Unknown  62s 235ms/step - loss: 1.4661 - sparse_categorical_accuracy: 0.4529


240/Unknown  62s 235ms/step - loss: 1.4646 - sparse_categorical_accuracy: 0.4534


241/Unknown  62s 235ms/step - loss: 1.4632 - sparse_categorical_accuracy: 0.4539


242/Unknown  62s 235ms/step - loss: 1.4618 - sparse_categorical_accuracy: 0.4544


243/Unknown  63s 235ms/step - loss: 1.4604 - sparse_categorical_accuracy: 0.4549


244/Unknown  63s 235ms/step - loss: 1.4591 - sparse_categorical_accuracy: 0.4554


245/Unknown  63s 235ms/step - loss: 1.4577 - sparse_categorical_accuracy: 0.4559


246/Unknown  63s 235ms/step - loss: 1.4563 - sparse_categorical_accuracy: 0.4564


247/Unknown  64s 235ms/step - loss: 1.4549 - sparse_categorical_accuracy: 0.4569


248/Unknown  64s 235ms/step - loss: 1.4536 - sparse_categorical_accuracy: 0.4574


249/Unknown  64s 235ms/step - loss: 1.4522 - sparse_categorical_accuracy: 0.4579


250/Unknown  64s 235ms/step - loss: 1.4509 - sparse_categorical_accuracy: 0.4584


251/Unknown  65s 235ms/step - loss: 1.4495 - sparse_categorical_accuracy: 0.4589


252/Unknown  65s 235ms/step - loss: 1.4482 - sparse_categorical_accuracy: 0.4593


253/Unknown  65s 235ms/step - loss: 1.4469 - sparse_categorical_accuracy: 0.4598


254/Unknown  65s 235ms/step - loss: 1.4455 - sparse_categorical_accuracy: 0.4603


255/Unknown  65s 235ms/step - loss: 1.4442 - sparse_categorical_accuracy: 0.4608


256/Unknown  66s 235ms/step - loss: 1.4429 - sparse_categorical_accuracy: 0.4612


257/Unknown  66s 235ms/step - loss: 1.4416 - sparse_categorical_accuracy: 0.4617


258/Unknown  66s 235ms/step - loss: 1.4403 - sparse_categorical_accuracy: 0.4622


259/Unknown  66s 235ms/step - loss: 1.4390 - sparse_categorical_accuracy: 0.4626


260/Unknown  67s 235ms/step - loss: 1.4377 - sparse_categorical_accuracy: 0.4631


261/Unknown  67s 235ms/step - loss: 1.4364 - sparse_categorical_accuracy: 0.4636


262/Unknown  67s 235ms/step - loss: 1.4352 - sparse_categorical_accuracy: 0.4640


263/Unknown  67s 235ms/step - loss: 1.4339 - sparse_categorical_accuracy: 0.4645


264/Unknown  68s 235ms/step - loss: 1.4326 - sparse_categorical_accuracy: 0.4649


265/Unknown  68s 235ms/step - loss: 1.4314 - sparse_categorical_accuracy: 0.4654


266/Unknown  68s 235ms/step - loss: 1.4301 - sparse_categorical_accuracy: 0.4658


267/Unknown  68s 235ms/step - loss: 1.4289 - sparse_categorical_accuracy: 0.4663


268/Unknown  69s 235ms/step - loss: 1.4276 - sparse_categorical_accuracy: 0.4667


269/Unknown  69s 236ms/step - loss: 1.4264 - sparse_categorical_accuracy: 0.4672


270/Unknown  69s 236ms/step - loss: 1.4251 - sparse_categorical_accuracy: 0.4676


271/Unknown  70s 236ms/step - loss: 1.4239 - sparse_categorical_accuracy: 0.4680


272/Unknown  70s 237ms/step - loss: 1.4227 - sparse_categorical_accuracy: 0.4685


273/Unknown  70s 237ms/step - loss: 1.4215 - sparse_categorical_accuracy: 0.4689


274/Unknown  70s 237ms/step - loss: 1.4202 - sparse_categorical_accuracy: 0.4694


275/Unknown  71s 237ms/step - loss: 1.4190 - sparse_categorical_accuracy: 0.4698


276/Unknown  71s 237ms/step - loss: 1.4178 - sparse_categorical_accuracy: 0.4702


277/Unknown  71s 237ms/step - loss: 1.4166 - sparse_categorical_accuracy: 0.4706


278/Unknown  71s 237ms/step - loss: 1.4154 - sparse_categorical_accuracy: 0.4711


279/Unknown  72s 237ms/step - loss: 1.4142 - sparse_categorical_accuracy: 0.4715


280/Unknown  72s 237ms/step - loss: 1.4131 - sparse_categorical_accuracy: 0.4719


281/Unknown  72s 237ms/step - loss: 1.4119 - sparse_categorical_accuracy: 0.4723


282/Unknown  72s 237ms/step - loss: 1.4107 - sparse_categorical_accuracy: 0.4728


283/Unknown  73s 237ms/step - loss: 1.4095 - sparse_categorical_accuracy: 0.4732


284/Unknown  73s 237ms/step - loss: 1.4084 - sparse_categorical_accuracy: 0.4736


285/Unknown  73s 237ms/step - loss: 1.4072 - sparse_categorical_accuracy: 0.4740


286/Unknown  73s 237ms/step - loss: 1.4061 - sparse_categorical_accuracy: 0.4744


287/Unknown  74s 237ms/step - loss: 1.4049 - sparse_categorical_accuracy: 0.4748


288/Unknown  74s 237ms/step - loss: 1.4038 - sparse_categorical_accuracy: 0.4752


289/Unknown  74s 238ms/step - loss: 1.4026 - sparse_categorical_accuracy: 0.4756


290/Unknown  74s 238ms/step - loss: 1.4015 - sparse_categorical_accuracy: 0.4760


291/Unknown  75s 238ms/step - loss: 1.4003 - sparse_categorical_accuracy: 0.4764


292/Unknown  75s 238ms/step - loss: 1.3992 - sparse_categorical_accuracy: 0.4768


293/Unknown  75s 238ms/step - loss: 1.3981 - sparse_categorical_accuracy: 0.4772


294/Unknown  75s 238ms/step - loss: 1.3970 - sparse_categorical_accuracy: 0.4776


295/Unknown  76s 238ms/step - loss: 1.3959 - sparse_categorical_accuracy: 0.4780


296/Unknown  76s 238ms/step - loss: 1.3947 - sparse_categorical_accuracy: 0.4784


297/Unknown  76s 238ms/step - loss: 1.3936 - sparse_categorical_accuracy: 0.4788


298/Unknown  77s 238ms/step - loss: 1.3925 - sparse_categorical_accuracy: 0.4792


299/Unknown  77s 238ms/step - loss: 1.3914 - sparse_categorical_accuracy: 0.4796


300/Unknown  77s 238ms/step - loss: 1.3904 - sparse_categorical_accuracy: 0.4800


301/Unknown  77s 238ms/step - loss: 1.3893 - sparse_categorical_accuracy: 0.4803


302/Unknown  78s 238ms/step - loss: 1.3882 - sparse_categorical_accuracy: 0.4807


303/Unknown  78s 238ms/step - loss: 1.3871 - sparse_categorical_accuracy: 0.4811


304/Unknown  78s 238ms/step - loss: 1.3860 - sparse_categorical_accuracy: 0.4815


305/Unknown  78s 238ms/step - loss: 1.3850 - sparse_categorical_accuracy: 0.4819


306/Unknown  79s 239ms/step - loss: 1.3839 - sparse_categorical_accuracy: 0.4822


307/Unknown  79s 239ms/step - loss: 1.3828 - sparse_categorical_accuracy: 0.4826


308/Unknown  79s 239ms/step - loss: 1.3818 - sparse_categorical_accuracy: 0.4830


309/Unknown  79s 239ms/step - loss: 1.3807 - sparse_categorical_accuracy: 0.4833


310/Unknown  79s 238ms/step - loss: 1.3797 - sparse_categorical_accuracy: 0.4837


311/Unknown  80s 238ms/step - loss: 1.3786 - sparse_categorical_accuracy: 0.4841


312/Unknown  80s 239ms/step - loss: 1.3776 - sparse_categorical_accuracy: 0.4844


313/Unknown  80s 239ms/step - loss: 1.3766 - sparse_categorical_accuracy: 0.4848


314/Unknown  80s 239ms/step - loss: 1.3755 - sparse_categorical_accuracy: 0.4852


315/Unknown  81s 239ms/step - loss: 1.3745 - sparse_categorical_accuracy: 0.4855


316/Unknown  81s 239ms/step - loss: 1.3735 - sparse_categorical_accuracy: 0.4859


317/Unknown  81s 239ms/step - loss: 1.3725 - sparse_categorical_accuracy: 0.4862


318/Unknown  81s 239ms/step - loss: 1.3715 - sparse_categorical_accuracy: 0.4866


319/Unknown  82s 239ms/step - loss: 1.3704 - sparse_categorical_accuracy: 0.4869


320/Unknown  82s 239ms/step - loss: 1.3694 - sparse_categorical_accuracy: 0.4873


321/Unknown  82s 239ms/step - loss: 1.3684 - sparse_categorical_accuracy: 0.4876


322/Unknown  82s 239ms/step - loss: 1.3674 - sparse_categorical_accuracy: 0.4880


323/Unknown  83s 239ms/step - loss: 1.3664 - sparse_categorical_accuracy: 0.4883


324/Unknown  83s 239ms/step - loss: 1.3655 - sparse_categorical_accuracy: 0.4887


325/Unknown  83s 239ms/step - loss: 1.3645 - sparse_categorical_accuracy: 0.4890


326/Unknown  83s 239ms/step - loss: 1.3635 - sparse_categorical_accuracy: 0.4894


327/Unknown  84s 239ms/step - loss: 1.3625 - sparse_categorical_accuracy: 0.4897


328/Unknown  84s 239ms/step - loss: 1.3615 - sparse_categorical_accuracy: 0.4901


329/Unknown  84s 239ms/step - loss: 1.3606 - sparse_categorical_accuracy: 0.4904


330/Unknown  85s 239ms/step - loss: 1.3596 - sparse_categorical_accuracy: 0.4907


331/Unknown  85s 240ms/step - loss: 1.3586 - sparse_categorical_accuracy: 0.4911


332/Unknown  85s 240ms/step - loss: 1.3577 - sparse_categorical_accuracy: 0.4914


333/Unknown  85s 240ms/step - loss: 1.3567 - sparse_categorical_accuracy: 0.4917


334/Unknown  86s 240ms/step - loss: 1.3558 - sparse_categorical_accuracy: 0.4921


335/Unknown  86s 240ms/step - loss: 1.3548 - sparse_categorical_accuracy: 0.4924


336/Unknown  86s 240ms/step - loss: 1.3539 - sparse_categorical_accuracy: 0.4927


337/Unknown  86s 240ms/step - loss: 1.3529 - sparse_categorical_accuracy: 0.4931


338/Unknown  87s 240ms/step - loss: 1.3520 - sparse_categorical_accuracy: 0.4934


339/Unknown  87s 240ms/step - loss: 1.3510 - sparse_categorical_accuracy: 0.4937


340/Unknown  87s 240ms/step - loss: 1.3501 - sparse_categorical_accuracy: 0.4940


341/Unknown  87s 240ms/step - loss: 1.3492 - sparse_categorical_accuracy: 0.4944


342/Unknown  88s 240ms/step - loss: 1.3483 - sparse_categorical_accuracy: 0.4947


343/Unknown  88s 240ms/step - loss: 1.3473 - sparse_categorical_accuracy: 0.4950


344/Unknown  88s 240ms/step - loss: 1.3464 - sparse_categorical_accuracy: 0.4953


345/Unknown  89s 240ms/step - loss: 1.3455 - sparse_categorical_accuracy: 0.4956


346/Unknown  89s 241ms/step - loss: 1.3446 - sparse_categorical_accuracy: 0.4959


347/Unknown  89s 241ms/step - loss: 1.3437 - sparse_categorical_accuracy: 0.4963


348/Unknown  89s 241ms/step - loss: 1.3428 - sparse_categorical_accuracy: 0.4966


349/Unknown  90s 241ms/step - loss: 1.3419 - sparse_categorical_accuracy: 0.4969


350/Unknown  90s 241ms/step - loss: 1.3410 - sparse_categorical_accuracy: 0.4972


351/Unknown  90s 241ms/step - loss: 1.3401 - sparse_categorical_accuracy: 0.4975


352/Unknown  90s 241ms/step - loss: 1.3392 - sparse_categorical_accuracy: 0.4978


353/Unknown  91s 241ms/step - loss: 1.3383 - sparse_categorical_accuracy: 0.4981


354/Unknown  91s 241ms/step - loss: 1.3374 - sparse_categorical_accuracy: 0.4984


355/Unknown  91s 241ms/step - loss: 1.3365 - sparse_categorical_accuracy: 0.4987


356/Unknown  92s 242ms/step - loss: 1.3356 - sparse_categorical_accuracy: 0.4990


357/Unknown  92s 242ms/step - loss: 1.3348 - sparse_categorical_accuracy: 0.4994


358/Unknown  92s 242ms/step - loss: 1.3339 - sparse_categorical_accuracy: 0.4997


359/Unknown  92s 242ms/step - loss: 1.3330 - sparse_categorical_accuracy: 0.5000


360/Unknown  93s 242ms/step - loss: 1.3321 - sparse_categorical_accuracy: 0.5003


361/Unknown  93s 242ms/step - loss: 1.3313 - sparse_categorical_accuracy: 0.5006


362/Unknown  93s 242ms/step - loss: 1.3304 - sparse_categorical_accuracy: 0.5009


363/Unknown  94s 243ms/step - loss: 1.3296 - sparse_categorical_accuracy: 0.5011


364/Unknown  94s 243ms/step - loss: 1.3287 - sparse_categorical_accuracy: 0.5014


365/Unknown  94s 243ms/step - loss: 1.3279 - sparse_categorical_accuracy: 0.5017


366/Unknown  94s 243ms/step - loss: 1.3270 - sparse_categorical_accuracy: 0.5020


367/Unknown  95s 242ms/step - loss: 1.3262 - sparse_categorical_accuracy: 0.5023


368/Unknown  95s 242ms/step - loss: 1.3253 - sparse_categorical_accuracy: 0.5026


369/Unknown  95s 243ms/step - loss: 1.3245 - sparse_categorical_accuracy: 0.5029


370/Unknown  95s 243ms/step - loss: 1.3236 - sparse_categorical_accuracy: 0.5032


371/Unknown  96s 243ms/step - loss: 1.3228 - sparse_categorical_accuracy: 0.5035


372/Unknown  96s 243ms/step - loss: 1.3220 - sparse_categorical_accuracy: 0.5038


373/Unknown  96s 243ms/step - loss: 1.3211 - sparse_categorical_accuracy: 0.5041


374/Unknown  96s 243ms/step - loss: 1.3203 - sparse_categorical_accuracy: 0.5043


375/Unknown  97s 243ms/step - loss: 1.3195 - sparse_categorical_accuracy: 0.5046


376/Unknown  97s 243ms/step - loss: 1.3187 - sparse_categorical_accuracy: 0.5049


377/Unknown  97s 243ms/step - loss: 1.3179 - sparse_categorical_accuracy: 0.5052


378/Unknown  97s 243ms/step - loss: 1.3170 - sparse_categorical_accuracy: 0.5055


379/Unknown  98s 243ms/step - loss: 1.3162 - sparse_categorical_accuracy: 0.5057


380/Unknown  98s 243ms/step - loss: 1.3154 - sparse_categorical_accuracy: 0.5060


381/Unknown  98s 243ms/step - loss: 1.3146 - sparse_categorical_accuracy: 0.5063


382/Unknown  98s 243ms/step - loss: 1.3138 - sparse_categorical_accuracy: 0.5066


383/Unknown  99s 243ms/step - loss: 1.3130 - sparse_categorical_accuracy: 0.5068


384/Unknown  99s 243ms/step - loss: 1.3122 - sparse_categorical_accuracy: 0.5071


385/Unknown  99s 243ms/step - loss: 1.3114 - sparse_categorical_accuracy: 0.5074


386/Unknown  99s 243ms/step - loss: 1.3106 - sparse_categorical_accuracy: 0.5077


387/Unknown  100s 243ms/step - loss: 1.3098 - sparse_categorical_accuracy: 0.5079


388/Unknown  100s 243ms/step - loss: 1.3091 - sparse_categorical_accuracy: 0.5082


389/Unknown  100s 243ms/step - loss: 1.3083 - sparse_categorical_accuracy: 0.5085


390/Unknown  101s 243ms/step - loss: 1.3075 - sparse_categorical_accuracy: 0.5087


391/Unknown  101s 244ms/step - loss: 1.3067 - sparse_categorical_accuracy: 0.5090


392/Unknown  101s 244ms/step - loss: 1.3059 - sparse_categorical_accuracy: 0.5093


393/Unknown  101s 244ms/step - loss: 1.3052 - sparse_categorical_accuracy: 0.5095


394/Unknown  102s 244ms/step - loss: 1.3044 - sparse_categorical_accuracy: 0.5098


395/Unknown  102s 244ms/step - loss: 1.3036 - sparse_categorical_accuracy: 0.5101


396/Unknown  102s 244ms/step - loss: 1.3029 - sparse_categorical_accuracy: 0.5103


397/Unknown  102s 244ms/step - loss: 1.3021 - sparse_categorical_accuracy: 0.5106


398/Unknown  103s 244ms/step - loss: 1.3013 - sparse_categorical_accuracy: 0.5108


399/Unknown  103s 244ms/step - loss: 1.3006 - sparse_categorical_accuracy: 0.5111


400/Unknown  103s 244ms/step - loss: 1.2998 - sparse_categorical_accuracy: 0.5114


401/Unknown  103s 244ms/step - loss: 1.2991 - sparse_categorical_accuracy: 0.5116


402/Unknown  104s 244ms/step - loss: 1.2983 - sparse_categorical_accuracy: 0.5119


403/Unknown  104s 244ms/step - loss: 1.2976 - sparse_categorical_accuracy: 0.5121


404/Unknown  104s 244ms/step - loss: 1.2968 - sparse_categorical_accuracy: 0.5124


405/Unknown  104s 244ms/step - loss: 1.2961 - sparse_categorical_accuracy: 0.5126


406/Unknown  105s 244ms/step - loss: 1.2953 - sparse_categorical_accuracy: 0.5129


407/Unknown  105s 244ms/step - loss: 1.2946 - sparse_categorical_accuracy: 0.5131


408/Unknown  105s 244ms/step - loss: 1.2939 - sparse_categorical_accuracy: 0.5134


409/Unknown  105s 244ms/step - loss: 1.2931 - sparse_categorical_accuracy: 0.5136


410/Unknown  106s 244ms/step - loss: 1.2924 - sparse_categorical_accuracy: 0.5139


411/Unknown  106s 244ms/step - loss: 1.2917 - sparse_categorical_accuracy: 0.5141


412/Unknown  106s 244ms/step - loss: 1.2909 - sparse_categorical_accuracy: 0.5144


413/Unknown  106s 244ms/step - loss: 1.2902 - sparse_categorical_accuracy: 0.5146


414/Unknown  107s 244ms/step - loss: 1.2895 - sparse_categorical_accuracy: 0.5149


415/Unknown  107s 244ms/step - loss: 1.2888 - sparse_categorical_accuracy: 0.5151


416/Unknown  107s 244ms/step - loss: 1.2880 - sparse_categorical_accuracy: 0.5154


417/Unknown  107s 244ms/step - loss: 1.2873 - sparse_categorical_accuracy: 0.5156


418/Unknown  108s 244ms/step - loss: 1.2866 - sparse_categorical_accuracy: 0.5159


419/Unknown  108s 244ms/step - loss: 1.2859 - sparse_categorical_accuracy: 0.5161


420/Unknown  108s 244ms/step - loss: 1.2852 - sparse_categorical_accuracy: 0.5163


421/Unknown  108s 244ms/step - loss: 1.2845 - sparse_categorical_accuracy: 0.5166


422/Unknown  109s 244ms/step - loss: 1.2838 - sparse_categorical_accuracy: 0.5168


423/Unknown  109s 244ms/step - loss: 1.2831 - sparse_categorical_accuracy: 0.5171


424/Unknown  109s 244ms/step - loss: 1.2824 - sparse_categorical_accuracy: 0.5173


425/Unknown  109s 244ms/step - loss: 1.2817 - sparse_categorical_accuracy: 0.5175


426/Unknown  110s 245ms/step - loss: 1.2810 - sparse_categorical_accuracy: 0.5178


427/Unknown  110s 245ms/step - loss: 1.2803 - sparse_categorical_accuracy: 0.5180


428/Unknown  110s 245ms/step - loss: 1.2796 - sparse_categorical_accuracy: 0.5182


429/Unknown  110s 245ms/step - loss: 1.2789 - sparse_categorical_accuracy: 0.5185


430/Unknown  111s 245ms/step - loss: 1.2782 - sparse_categorical_accuracy: 0.5187


431/Unknown  111s 245ms/step - loss: 1.2775 - sparse_categorical_accuracy: 0.5189


432/Unknown  111s 245ms/step - loss: 1.2768 - sparse_categorical_accuracy: 0.5192


433/Unknown  112s 245ms/step - loss: 1.2762 - sparse_categorical_accuracy: 0.5194


434/Unknown  112s 245ms/step - loss: 1.2755 - sparse_categorical_accuracy: 0.5196


435/Unknown  112s 245ms/step - loss: 1.2748 - sparse_categorical_accuracy: 0.5199


436/Unknown  113s 245ms/step - loss: 1.2741 - sparse_categorical_accuracy: 0.5201


437/Unknown  113s 246ms/step - loss: 1.2735 - sparse_categorical_accuracy: 0.5203


438/Unknown  113s 246ms/step - loss: 1.2728 - sparse_categorical_accuracy: 0.5206


439/Unknown  113s 246ms/step - loss: 1.2721 - sparse_categorical_accuracy: 0.5208


440/Unknown  114s 246ms/step - loss: 1.2714 - sparse_categorical_accuracy: 0.5210


441/Unknown  114s 246ms/step - loss: 1.2708 - sparse_categorical_accuracy: 0.5212


442/Unknown  114s 246ms/step - loss: 1.2701 - sparse_categorical_accuracy: 0.5215


443/Unknown  115s 246ms/step - loss: 1.2695 - sparse_categorical_accuracy: 0.5217


444/Unknown  115s 246ms/step - loss: 1.2688 - sparse_categorical_accuracy: 0.5219


445/Unknown  115s 246ms/step - loss: 1.2681 - sparse_categorical_accuracy: 0.5221


446/Unknown  115s 246ms/step - loss: 1.2675 - sparse_categorical_accuracy: 0.5224


447/Unknown  116s 247ms/step - loss: 1.2668 - sparse_categorical_accuracy: 0.5226


448/Unknown  116s 247ms/step - loss: 1.2662 - sparse_categorical_accuracy: 0.5228


449/Unknown  116s 247ms/step - loss: 1.2655 - sparse_categorical_accuracy: 0.5230


450/Unknown  117s 247ms/step - loss: 1.2649 - sparse_categorical_accuracy: 0.5232


451/Unknown  117s 247ms/step - loss: 1.2642 - sparse_categorical_accuracy: 0.5235


452/Unknown  117s 247ms/step - loss: 1.2636 - sparse_categorical_accuracy: 0.5237


453/Unknown  117s 247ms/step - loss: 1.2630 - sparse_categorical_accuracy: 0.5239


454/Unknown  118s 247ms/step - loss: 1.2623 - sparse_categorical_accuracy: 0.5241


455/Unknown  118s 247ms/step - loss: 1.2617 - sparse_categorical_accuracy: 0.5243


456/Unknown  118s 247ms/step - loss: 1.2610 - sparse_categorical_accuracy: 0.5245


457/Unknown  118s 247ms/step - loss: 1.2604 - sparse_categorical_accuracy: 0.5248


458/Unknown  119s 247ms/step - loss: 1.2598 - sparse_categorical_accuracy: 0.5250


459/Unknown  119s 247ms/step - loss: 1.2591 - sparse_categorical_accuracy: 0.5252


460/Unknown  119s 247ms/step - loss: 1.2585 - sparse_categorical_accuracy: 0.5254


461/Unknown  119s 247ms/step - loss: 1.2579 - sparse_categorical_accuracy: 0.5256


462/Unknown  120s 247ms/step - loss: 1.2573 - sparse_categorical_accuracy: 0.5258


463/Unknown  120s 247ms/step - loss: 1.2566 - sparse_categorical_accuracy: 0.5260


464/Unknown  120s 247ms/step - loss: 1.2560 - sparse_categorical_accuracy: 0.5262


465/Unknown  121s 247ms/step - loss: 1.2554 - sparse_categorical_accuracy: 0.5264


466/Unknown  121s 247ms/step - loss: 1.2548 - sparse_categorical_accuracy: 0.5267


467/Unknown  121s 247ms/step - loss: 1.2541 - sparse_categorical_accuracy: 0.5269


468/Unknown  121s 247ms/step - loss: 1.2535 - sparse_categorical_accuracy: 0.5271


469/Unknown  122s 247ms/step - loss: 1.2529 - sparse_categorical_accuracy: 0.5273


470/Unknown  122s 248ms/step - loss: 1.2523 - sparse_categorical_accuracy: 0.5275


471/Unknown  122s 248ms/step - loss: 1.2517 - sparse_categorical_accuracy: 0.5277


472/Unknown  123s 248ms/step - loss: 1.2511 - sparse_categorical_accuracy: 0.5279


473/Unknown  123s 248ms/step - loss: 1.2505 - sparse_categorical_accuracy: 0.5281


474/Unknown  123s 248ms/step - loss: 1.2499 - sparse_categorical_accuracy: 0.5283


475/Unknown  124s 249ms/step - loss: 1.2493 - sparse_categorical_accuracy: 0.5285


476/Unknown  124s 249ms/step - loss: 1.2487 - sparse_categorical_accuracy: 0.5287


477/Unknown  124s 249ms/step - loss: 1.2481 - sparse_categorical_accuracy: 0.5289


478/Unknown  124s 249ms/step - loss: 1.2475 - sparse_categorical_accuracy: 0.5291


479/Unknown  125s 249ms/step - loss: 1.2469 - sparse_categorical_accuracy: 0.5293


480/Unknown  125s 249ms/step - loss: 1.2463 - sparse_categorical_accuracy: 0.5295


481/Unknown  125s 249ms/step - loss: 1.2457 - sparse_categorical_accuracy: 0.5297


482/Unknown  125s 248ms/step - loss: 1.2451 - sparse_categorical_accuracy: 0.5299


483/Unknown  126s 248ms/step - loss: 1.2445 - sparse_categorical_accuracy: 0.5301


484/Unknown  126s 249ms/step - loss: 1.2439 - sparse_categorical_accuracy: 0.5303


485/Unknown  126s 249ms/step - loss: 1.2433 - sparse_categorical_accuracy: 0.5305


486/Unknown  126s 249ms/step - loss: 1.2427 - sparse_categorical_accuracy: 0.5307


487/Unknown  127s 249ms/step - loss: 1.2421 - sparse_categorical_accuracy: 0.5309


488/Unknown  127s 249ms/step - loss: 1.2416 - sparse_categorical_accuracy: 0.5311


489/Unknown  127s 249ms/step - loss: 1.2410 - sparse_categorical_accuracy: 0.5313


490/Unknown  127s 249ms/step - loss: 1.2404 - sparse_categorical_accuracy: 0.5315


491/Unknown  128s 249ms/step - loss: 1.2398 - sparse_categorical_accuracy: 0.5317


492/Unknown  128s 249ms/step - loss: 1.2392 - sparse_categorical_accuracy: 0.5319


493/Unknown  128s 249ms/step - loss: 1.2387 - sparse_categorical_accuracy: 0.5321


494/Unknown  129s 249ms/step - loss: 1.2381 - sparse_categorical_accuracy: 0.5323


495/Unknown  129s 249ms/step - loss: 1.2375 - sparse_categorical_accuracy: 0.5325


496/Unknown  129s 249ms/step - loss: 1.2369 - sparse_categorical_accuracy: 0.5326


497/Unknown  129s 249ms/step - loss: 1.2364 - sparse_categorical_accuracy: 0.5328


498/Unknown  130s 249ms/step - loss: 1.2358 - sparse_categorical_accuracy: 0.5330


499/Unknown  130s 249ms/step - loss: 1.2352 - sparse_categorical_accuracy: 0.5332


500/Unknown  130s 249ms/step - loss: 1.2347 - sparse_categorical_accuracy: 0.5334


501/Unknown  130s 249ms/step - loss: 1.2341 - sparse_categorical_accuracy: 0.5336


502/Unknown  131s 249ms/step - loss: 1.2336 - sparse_categorical_accuracy: 0.5338


503/Unknown  131s 249ms/step - loss: 1.2330 - sparse_categorical_accuracy: 0.5340


504/Unknown  131s 249ms/step - loss: 1.2324 - sparse_categorical_accuracy: 0.5342


505/Unknown  131s 249ms/step - loss: 1.2319 - sparse_categorical_accuracy: 0.5343


506/Unknown  132s 249ms/step - loss: 1.2313 - sparse_categorical_accuracy: 0.5345


507/Unknown  132s 250ms/step - loss: 1.2308 - sparse_categorical_accuracy: 0.5347


508/Unknown  133s 250ms/step - loss: 1.2302 - sparse_categorical_accuracy: 0.5349


509/Unknown  133s 250ms/step - loss: 1.2297 - sparse_categorical_accuracy: 0.5351


510/Unknown  133s 250ms/step - loss: 1.2291 - sparse_categorical_accuracy: 0.5353


511/Unknown  133s 250ms/step - loss: 1.2286 - sparse_categorical_accuracy: 0.5355


512/Unknown  134s 250ms/step - loss: 1.2280 - sparse_categorical_accuracy: 0.5356


513/Unknown  134s 250ms/step - loss: 1.2275 - sparse_categorical_accuracy: 0.5358


514/Unknown  134s 250ms/step - loss: 1.2269 - sparse_categorical_accuracy: 0.5360


515/Unknown  134s 250ms/step - loss: 1.2264 - sparse_categorical_accuracy: 0.5362


516/Unknown  135s 250ms/step - loss: 1.2258 - sparse_categorical_accuracy: 0.5364


517/Unknown  135s 250ms/step - loss: 1.2253 - sparse_categorical_accuracy: 0.5366


518/Unknown  135s 250ms/step - loss: 1.2248 - sparse_categorical_accuracy: 0.5367


519/Unknown  136s 251ms/step - loss: 1.2242 - sparse_categorical_accuracy: 0.5369


520/Unknown  136s 251ms/step - loss: 1.2237 - sparse_categorical_accuracy: 0.5371


521/Unknown  136s 251ms/step - loss: 1.2231 - sparse_categorical_accuracy: 0.5373


522/Unknown  136s 251ms/step - loss: 1.2226 - sparse_categorical_accuracy: 0.5375


523/Unknown  137s 251ms/step - loss: 1.2221 - sparse_categorical_accuracy: 0.5376


524/Unknown  137s 251ms/step - loss: 1.2215 - sparse_categorical_accuracy: 0.5378


525/Unknown  137s 251ms/step - loss: 1.2210 - sparse_categorical_accuracy: 0.5380


526/Unknown  137s 251ms/step - loss: 1.2205 - sparse_categorical_accuracy: 0.5382


527/Unknown  138s 251ms/step - loss: 1.2200 - sparse_categorical_accuracy: 0.5383


528/Unknown  138s 251ms/step - loss: 1.2194 - sparse_categorical_accuracy: 0.5385


529/Unknown  138s 251ms/step - loss: 1.2189 - sparse_categorical_accuracy: 0.5387


530/Unknown  138s 251ms/step - loss: 1.2184 - sparse_categorical_accuracy: 0.5389


531/Unknown  139s 251ms/step - loss: 1.2179 - sparse_categorical_accuracy: 0.5390


532/Unknown  139s 251ms/step - loss: 1.2173 - sparse_categorical_accuracy: 0.5392


533/Unknown  139s 251ms/step - loss: 1.2168 - sparse_categorical_accuracy: 0.5394


534/Unknown  140s 251ms/step - loss: 1.2163 - sparse_categorical_accuracy: 0.5396


535/Unknown  140s 251ms/step - loss: 1.2158 - sparse_categorical_accuracy: 0.5397


536/Unknown  140s 251ms/step - loss: 1.2153 - sparse_categorical_accuracy: 0.5399


537/Unknown  140s 251ms/step - loss: 1.2148 - sparse_categorical_accuracy: 0.5401


538/Unknown  141s 251ms/step - loss: 1.2142 - sparse_categorical_accuracy: 0.5402


539/Unknown  141s 251ms/step - loss: 1.2137 - sparse_categorical_accuracy: 0.5404


540/Unknown  141s 251ms/step - loss: 1.2132 - sparse_categorical_accuracy: 0.5406


541/Unknown  141s 251ms/step - loss: 1.2127 - sparse_categorical_accuracy: 0.5408


542/Unknown  142s 251ms/step - loss: 1.2122 - sparse_categorical_accuracy: 0.5409


543/Unknown  142s 251ms/step - loss: 1.2117 - sparse_categorical_accuracy: 0.5411


544/Unknown  142s 251ms/step - loss: 1.2112 - sparse_categorical_accuracy: 0.5413


545/Unknown  143s 252ms/step - loss: 1.2107 - sparse_categorical_accuracy: 0.5414


546/Unknown  143s 252ms/step - loss: 1.2102 - sparse_categorical_accuracy: 0.5416


547/Unknown  143s 252ms/step - loss: 1.2097 - sparse_categorical_accuracy: 0.5418


548/Unknown  144s 252ms/step - loss: 1.2092 - sparse_categorical_accuracy: 0.5419


549/Unknown  144s 252ms/step - loss: 1.2087 - sparse_categorical_accuracy: 0.5421


550/Unknown  144s 252ms/step - loss: 1.2082 - sparse_categorical_accuracy: 0.5423


551/Unknown  144s 252ms/step - loss: 1.2077 - sparse_categorical_accuracy: 0.5424


552/Unknown  145s 252ms/step - loss: 1.2072 - sparse_categorical_accuracy: 0.5426


553/Unknown  145s 252ms/step - loss: 1.2067 - sparse_categorical_accuracy: 0.5428


554/Unknown  145s 252ms/step - loss: 1.2062 - sparse_categorical_accuracy: 0.5429


555/Unknown  146s 252ms/step - loss: 1.2057 - sparse_categorical_accuracy: 0.5431


556/Unknown  146s 252ms/step - loss: 1.2052 - sparse_categorical_accuracy: 0.5433


557/Unknown  146s 252ms/step - loss: 1.2047 - sparse_categorical_accuracy: 0.5434


558/Unknown  146s 253ms/step - loss: 1.2043 - sparse_categorical_accuracy: 0.5436


559/Unknown  147s 253ms/step - loss: 1.2038 - sparse_categorical_accuracy: 0.5437


560/Unknown  147s 253ms/step - loss: 1.2033 - sparse_categorical_accuracy: 0.5439


561/Unknown  147s 253ms/step - loss: 1.2028 - sparse_categorical_accuracy: 0.5441


562/Unknown  148s 253ms/step - loss: 1.2023 - sparse_categorical_accuracy: 0.5442


563/Unknown  148s 253ms/step - loss: 1.2018 - sparse_categorical_accuracy: 0.5444


564/Unknown  148s 253ms/step - loss: 1.2013 - sparse_categorical_accuracy: 0.5445


565/Unknown  148s 253ms/step - loss: 1.2009 - sparse_categorical_accuracy: 0.5447


566/Unknown  149s 253ms/step - loss: 1.2004 - sparse_categorical_accuracy: 0.5449


567/Unknown  149s 253ms/step - loss: 1.1999 - sparse_categorical_accuracy: 0.5450


568/Unknown  149s 253ms/step - loss: 1.1994 - sparse_categorical_accuracy: 0.5452


569/Unknown  149s 253ms/step - loss: 1.1990 - sparse_categorical_accuracy: 0.5453


570/Unknown  150s 253ms/step - loss: 1.1985 - sparse_categorical_accuracy: 0.5455


571/Unknown  150s 253ms/step - loss: 1.1980 - sparse_categorical_accuracy: 0.5456


572/Unknown  150s 253ms/step - loss: 1.1975 - sparse_categorical_accuracy: 0.5458


573/Unknown  150s 253ms/step - loss: 1.1971 - sparse_categorical_accuracy: 0.5460


574/Unknown  150s 252ms/step - loss: 1.1966 - sparse_categorical_accuracy: 0.5461


575/Unknown  151s 252ms/step - loss: 1.1961 - sparse_categorical_accuracy: 0.5463


576/Unknown  151s 252ms/step - loss: 1.1957 - sparse_categorical_accuracy: 0.5464


577/Unknown  151s 252ms/step - loss: 1.1952 - sparse_categorical_accuracy: 0.5466


578/Unknown  151s 252ms/step - loss: 1.1947 - sparse_categorical_accuracy: 0.5467


579/Unknown  152s 252ms/step - loss: 1.1943 - sparse_categorical_accuracy: 0.5469


580/Unknown  152s 252ms/step - loss: 1.1938 - sparse_categorical_accuracy: 0.5470


581/Unknown  152s 252ms/step - loss: 1.1934 - sparse_categorical_accuracy: 0.5472


582/Unknown  152s 252ms/step - loss: 1.1929 - sparse_categorical_accuracy: 0.5473


583/Unknown  153s 252ms/step - loss: 1.1924 - sparse_categorical_accuracy: 0.5475


584/Unknown  153s 252ms/step - loss: 1.1920 - sparse_categorical_accuracy: 0.5476


585/Unknown  153s 252ms/step - loss: 1.1915 - sparse_categorical_accuracy: 0.5478


586/Unknown  153s 252ms/step - loss: 1.1911 - sparse_categorical_accuracy: 0.5479


587/Unknown  153s 252ms/step - loss: 1.1906 - sparse_categorical_accuracy: 0.5481


588/Unknown  154s 252ms/step - loss: 1.1901 - sparse_categorical_accuracy: 0.5482


589/Unknown  154s 252ms/step - loss: 1.1897 - sparse_categorical_accuracy: 0.5484


590/Unknown  154s 252ms/step - loss: 1.1892 - sparse_categorical_accuracy: 0.5485


591/Unknown  155s 252ms/step - loss: 1.1888 - sparse_categorical_accuracy: 0.5487


592/Unknown  155s 252ms/step - loss: 1.1883 - sparse_categorical_accuracy: 0.5488


593/Unknown  155s 252ms/step - loss: 1.1879 - sparse_categorical_accuracy: 0.5490


594/Unknown  155s 252ms/step - loss: 1.1874 - sparse_categorical_accuracy: 0.5491


595/Unknown  156s 252ms/step - loss: 1.1870 - sparse_categorical_accuracy: 0.5493


596/Unknown  156s 252ms/step - loss: 1.1865 - sparse_categorical_accuracy: 0.5494


597/Unknown  156s 252ms/step - loss: 1.1861 - sparse_categorical_accuracy: 0.5496


598/Unknown  156s 252ms/step - loss: 1.1857 - sparse_categorical_accuracy: 0.5497


599/Unknown  157s 252ms/step - loss: 1.1852 - sparse_categorical_accuracy: 0.5499


600/Unknown  157s 252ms/step - loss: 1.1848 - sparse_categorical_accuracy: 0.5500


601/Unknown  157s 252ms/step - loss: 1.1843 - sparse_categorical_accuracy: 0.5502


602/Unknown  157s 252ms/step - loss: 1.1839 - sparse_categorical_accuracy: 0.5503


603/Unknown  158s 252ms/step - loss: 1.1834 - sparse_categorical_accuracy: 0.5505


604/Unknown  158s 252ms/step - loss: 1.1830 - sparse_categorical_accuracy: 0.5506


605/Unknown  158s 252ms/step - loss: 1.1826 - sparse_categorical_accuracy: 0.5508


606/Unknown  158s 252ms/step - loss: 1.1821 - sparse_categorical_accuracy: 0.5509


607/Unknown  159s 252ms/step - loss: 1.1817 - sparse_categorical_accuracy: 0.5510


608/Unknown  159s 252ms/step - loss: 1.1813 - sparse_categorical_accuracy: 0.5512


609/Unknown  159s 252ms/step - loss: 1.1808 - sparse_categorical_accuracy: 0.5513


610/Unknown  159s 252ms/step - loss: 1.1804 - sparse_categorical_accuracy: 0.5515


611/Unknown  160s 252ms/step - loss: 1.1800 - sparse_categorical_accuracy: 0.5516


612/Unknown  160s 252ms/step - loss: 1.1795 - sparse_categorical_accuracy: 0.5518


613/Unknown  160s 252ms/step - loss: 1.1791 - sparse_categorical_accuracy: 0.5519


614/Unknown  160s 252ms/step - loss: 1.1787 - sparse_categorical_accuracy: 0.5520


615/Unknown  161s 252ms/step - loss: 1.1782 - sparse_categorical_accuracy: 0.5522


616/Unknown  161s 252ms/step - loss: 1.1778 - sparse_categorical_accuracy: 0.5523


617/Unknown  161s 252ms/step - loss: 1.1774 - sparse_categorical_accuracy: 0.5525


618/Unknown  161s 252ms/step - loss: 1.1770 - sparse_categorical_accuracy: 0.5526


619/Unknown  162s 252ms/step - loss: 1.1765 - sparse_categorical_accuracy: 0.5527


620/Unknown  162s 252ms/step - loss: 1.1761 - sparse_categorical_accuracy: 0.5529


621/Unknown  162s 252ms/step - loss: 1.1757 - sparse_categorical_accuracy: 0.5530


622/Unknown  163s 252ms/step - loss: 1.1753 - sparse_categorical_accuracy: 0.5532


623/Unknown  163s 252ms/step - loss: 1.1749 - sparse_categorical_accuracy: 0.5533


624/Unknown  163s 252ms/step - loss: 1.1744 - sparse_categorical_accuracy: 0.5534


625/Unknown  163s 252ms/step - loss: 1.1740 - sparse_categorical_accuracy: 0.5536


626/Unknown  164s 252ms/step - loss: 1.1736 - sparse_categorical_accuracy: 0.5537


627/Unknown  164s 252ms/step - loss: 1.1732 - sparse_categorical_accuracy: 0.5538


628/Unknown  164s 253ms/step - loss: 1.1728 - sparse_categorical_accuracy: 0.5540


629/Unknown  164s 253ms/step - loss: 1.1724 - sparse_categorical_accuracy: 0.5541


630/Unknown  165s 253ms/step - loss: 1.1719 - sparse_categorical_accuracy: 0.5543


631/Unknown  165s 253ms/step - loss: 1.1715 - sparse_categorical_accuracy: 0.5544


632/Unknown  165s 253ms/step - loss: 1.1711 - sparse_categorical_accuracy: 0.5545


633/Unknown  166s 253ms/step - loss: 1.1707 - sparse_categorical_accuracy: 0.5547


634/Unknown  166s 253ms/step - loss: 1.1703 - sparse_categorical_accuracy: 0.5548


635/Unknown  166s 253ms/step - loss: 1.1699 - sparse_categorical_accuracy: 0.5549


636/Unknown  167s 253ms/step - loss: 1.1695 - sparse_categorical_accuracy: 0.5551


637/Unknown  167s 253ms/step - loss: 1.1691 - sparse_categorical_accuracy: 0.5552


638/Unknown  167s 253ms/step - loss: 1.1687 - sparse_categorical_accuracy: 0.5553


639/Unknown  167s 253ms/step - loss: 1.1683 - sparse_categorical_accuracy: 0.5555


640/Unknown  168s 253ms/step - loss: 1.1678 - sparse_categorical_accuracy: 0.5556


641/Unknown  168s 253ms/step - loss: 1.1674 - sparse_categorical_accuracy: 0.5557


642/Unknown  168s 253ms/step - loss: 1.1670 - sparse_categorical_accuracy: 0.5559


643/Unknown  169s 253ms/step - loss: 1.1666 - sparse_categorical_accuracy: 0.5560


644/Unknown  169s 253ms/step - loss: 1.1662 - sparse_categorical_accuracy: 0.5561


645/Unknown  169s 253ms/step - loss: 1.1658 - sparse_categorical_accuracy: 0.5563


646/Unknown  169s 253ms/step - loss: 1.1654 - sparse_categorical_accuracy: 0.5564


647/Unknown  170s 253ms/step - loss: 1.1650 - sparse_categorical_accuracy: 0.5565


648/Unknown  170s 253ms/step - loss: 1.1646 - sparse_categorical_accuracy: 0.5567


649/Unknown  170s 253ms/step - loss: 1.1642 - sparse_categorical_accuracy: 0.5568


650/Unknown  170s 253ms/step - loss: 1.1638 - sparse_categorical_accuracy: 0.5569


651/Unknown  171s 254ms/step - loss: 1.1634 - sparse_categorical_accuracy: 0.5570


652/Unknown  171s 254ms/step - loss: 1.1630 - sparse_categorical_accuracy: 0.5572


653/Unknown  171s 254ms/step - loss: 1.1627 - sparse_categorical_accuracy: 0.5573


654/Unknown  171s 254ms/step - loss: 1.1623 - sparse_categorical_accuracy: 0.5574


655/Unknown  172s 254ms/step - loss: 1.1619 - sparse_categorical_accuracy: 0.5576


656/Unknown  172s 254ms/step - loss: 1.1615 - sparse_categorical_accuracy: 0.5577


657/Unknown  172s 254ms/step - loss: 1.1611 - sparse_categorical_accuracy: 0.5578


658/Unknown  173s 254ms/step - loss: 1.1607 - sparse_categorical_accuracy: 0.5579


659/Unknown  173s 254ms/step - loss: 1.1603 - sparse_categorical_accuracy: 0.5581


660/Unknown  173s 254ms/step - loss: 1.1599 - sparse_categorical_accuracy: 0.5582


661/Unknown  173s 254ms/step - loss: 1.1595 - sparse_categorical_accuracy: 0.5583


662/Unknown  174s 254ms/step - loss: 1.1591 - sparse_categorical_accuracy: 0.5584


663/Unknown  174s 254ms/step - loss: 1.1588 - sparse_categorical_accuracy: 0.5586


664/Unknown  174s 254ms/step - loss: 1.1584 - sparse_categorical_accuracy: 0.5587


665/Unknown  175s 254ms/step - loss: 1.1580 - sparse_categorical_accuracy: 0.5588


666/Unknown  175s 254ms/step - loss: 1.1576 - sparse_categorical_accuracy: 0.5590


667/Unknown  175s 255ms/step - loss: 1.1572 - sparse_categorical_accuracy: 0.5591


668/Unknown  176s 255ms/step - loss: 1.1568 - sparse_categorical_accuracy: 0.5592


669/Unknown  176s 255ms/step - loss: 1.1565 - sparse_categorical_accuracy: 0.5593


670/Unknown  176s 255ms/step - loss: 1.1561 - sparse_categorical_accuracy: 0.5595


671/Unknown  177s 255ms/step - loss: 1.1557 - sparse_categorical_accuracy: 0.5596


672/Unknown  177s 255ms/step - loss: 1.1553 - sparse_categorical_accuracy: 0.5597


673/Unknown  177s 255ms/step - loss: 1.1549 - sparse_categorical_accuracy: 0.5598


674/Unknown  177s 255ms/step - loss: 1.1546 - sparse_categorical_accuracy: 0.5600


675/Unknown  178s 255ms/step - loss: 1.1542 - sparse_categorical_accuracy: 0.5601


676/Unknown  178s 255ms/step - loss: 1.1538 - sparse_categorical_accuracy: 0.5602


677/Unknown  178s 255ms/step - loss: 1.1534 - sparse_categorical_accuracy: 0.5603


678/Unknown  178s 255ms/step - loss: 1.1531 - sparse_categorical_accuracy: 0.5604


679/Unknown  179s 255ms/step - loss: 1.1527 - sparse_categorical_accuracy: 0.5606


680/Unknown  179s 255ms/step - loss: 1.1523 - sparse_categorical_accuracy: 0.5607


681/Unknown  179s 255ms/step - loss: 1.1519 - sparse_categorical_accuracy: 0.5608


682/Unknown  179s 255ms/step - loss: 1.1516 - sparse_categorical_accuracy: 0.5609


683/Unknown  180s 255ms/step - loss: 1.1512 - sparse_categorical_accuracy: 0.5611


684/Unknown  180s 255ms/step - loss: 1.1508 - sparse_categorical_accuracy: 0.5612


685/Unknown  180s 255ms/step - loss: 1.1505 - sparse_categorical_accuracy: 0.5613


686/Unknown  180s 255ms/step - loss: 1.1501 - sparse_categorical_accuracy: 0.5614


687/Unknown  180s 255ms/step - loss: 1.1497 - sparse_categorical_accuracy: 0.5615


688/Unknown  181s 255ms/step - loss: 1.1494 - sparse_categorical_accuracy: 0.5617


689/Unknown  181s 255ms/step - loss: 1.1490 - sparse_categorical_accuracy: 0.5618


690/Unknown  181s 254ms/step - loss: 1.1486 - sparse_categorical_accuracy: 0.5619


691/Unknown  181s 254ms/step - loss: 1.1483 - sparse_categorical_accuracy: 0.5620


692/Unknown  182s 254ms/step - loss: 1.1479 - sparse_categorical_accuracy: 0.5621


693/Unknown  182s 254ms/step - loss: 1.1475 - sparse_categorical_accuracy: 0.5623


694/Unknown  182s 254ms/step - loss: 1.1472 - sparse_categorical_accuracy: 0.5624


695/Unknown  182s 254ms/step - loss: 1.1468 - sparse_categorical_accuracy: 0.5625


696/Unknown  183s 254ms/step - loss: 1.1464 - sparse_categorical_accuracy: 0.5626


697/Unknown  183s 254ms/step - loss: 1.1461 - sparse_categorical_accuracy: 0.5627


698/Unknown  183s 254ms/step - loss: 1.1457 - sparse_categorical_accuracy: 0.5628


699/Unknown  183s 255ms/step - loss: 1.1454 - sparse_categorical_accuracy: 0.5630


700/Unknown  184s 255ms/step - loss: 1.1450 - sparse_categorical_accuracy: 0.5631


701/Unknown  184s 255ms/step - loss: 1.1447 - sparse_categorical_accuracy: 0.5632


702/Unknown  184s 255ms/step - loss: 1.1443 - sparse_categorical_accuracy: 0.5633


703/Unknown  185s 255ms/step - loss: 1.1439 - sparse_categorical_accuracy: 0.5634


704/Unknown  185s 255ms/step - loss: 1.1436 - sparse_categorical_accuracy: 0.5635


705/Unknown  185s 255ms/step - loss: 1.1432 - sparse_categorical_accuracy: 0.5637


706/Unknown  185s 255ms/step - loss: 1.1429 - sparse_categorical_accuracy: 0.5638


707/Unknown  186s 255ms/step - loss: 1.1425 - sparse_categorical_accuracy: 0.5639


708/Unknown  186s 255ms/step - loss: 1.1422 - sparse_categorical_accuracy: 0.5640


709/Unknown  186s 255ms/step - loss: 1.1418 - sparse_categorical_accuracy: 0.5641


710/Unknown  187s 255ms/step - loss: 1.1415 - sparse_categorical_accuracy: 0.5642


711/Unknown  187s 255ms/step - loss: 1.1411 - sparse_categorical_accuracy: 0.5644


712/Unknown  187s 255ms/step - loss: 1.1408 - sparse_categorical_accuracy: 0.5645


713/Unknown  188s 255ms/step - loss: 1.1404 - sparse_categorical_accuracy: 0.5646


714/Unknown  188s 255ms/step - loss: 1.1401 - sparse_categorical_accuracy: 0.5647


715/Unknown  188s 255ms/step - loss: 1.1397 - sparse_categorical_accuracy: 0.5648


716/Unknown  188s 255ms/step - loss: 1.1394 - sparse_categorical_accuracy: 0.5649


717/Unknown  189s 255ms/step - loss: 1.1390 - sparse_categorical_accuracy: 0.5650


718/Unknown  189s 256ms/step - loss: 1.1387 - sparse_categorical_accuracy: 0.5651


719/Unknown  189s 256ms/step - loss: 1.1383 - sparse_categorical_accuracy: 0.5653


720/Unknown  190s 256ms/step - loss: 1.1380 - sparse_categorical_accuracy: 0.5654


721/Unknown  190s 256ms/step - loss: 1.1376 - sparse_categorical_accuracy: 0.5655


722/Unknown  190s 256ms/step - loss: 1.1373 - sparse_categorical_accuracy: 0.5656


723/Unknown  191s 256ms/step - loss: 1.1370 - sparse_categorical_accuracy: 0.5657


724/Unknown  191s 256ms/step - loss: 1.1366 - sparse_categorical_accuracy: 0.5658


725/Unknown  191s 256ms/step - loss: 1.1363 - sparse_categorical_accuracy: 0.5659


726/Unknown  192s 256ms/step - loss: 1.1359 - sparse_categorical_accuracy: 0.5660


727/Unknown  192s 256ms/step - loss: 1.1356 - sparse_categorical_accuracy: 0.5662


728/Unknown  192s 256ms/step - loss: 1.1353 - sparse_categorical_accuracy: 0.5663


729/Unknown  192s 256ms/step - loss: 1.1349 - sparse_categorical_accuracy: 0.5664


730/Unknown  193s 256ms/step - loss: 1.1346 - sparse_categorical_accuracy: 0.5665


731/Unknown  193s 256ms/step - loss: 1.1342 - sparse_categorical_accuracy: 0.5666


732/Unknown  193s 256ms/step - loss: 1.1339 - sparse_categorical_accuracy: 0.5667


733/Unknown  193s 256ms/step - loss: 1.1336 - sparse_categorical_accuracy: 0.5668


734/Unknown  194s 256ms/step - loss: 1.1332 - sparse_categorical_accuracy: 0.5669


735/Unknown  194s 256ms/step - loss: 1.1329 - sparse_categorical_accuracy: 0.5670


736/Unknown  194s 256ms/step - loss: 1.1326 - sparse_categorical_accuracy: 0.5671


737/Unknown  194s 256ms/step - loss: 1.1322 - sparse_categorical_accuracy: 0.5672


738/Unknown  195s 256ms/step - loss: 1.1319 - sparse_categorical_accuracy: 0.5674


739/Unknown  195s 256ms/step - loss: 1.1316 - sparse_categorical_accuracy: 0.5675


740/Unknown  195s 256ms/step - loss: 1.1312 - sparse_categorical_accuracy: 0.5676


741/Unknown  195s 256ms/step - loss: 1.1309 - sparse_categorical_accuracy: 0.5677


742/Unknown  196s 256ms/step - loss: 1.1306 - sparse_categorical_accuracy: 0.5678


743/Unknown  196s 256ms/step - loss: 1.1302 - sparse_categorical_accuracy: 0.5679


744/Unknown  196s 256ms/step - loss: 1.1299 - sparse_categorical_accuracy: 0.5680


745/Unknown  196s 256ms/step - loss: 1.1296 - sparse_categorical_accuracy: 0.5681


746/Unknown  197s 256ms/step - loss: 1.1293 - sparse_categorical_accuracy: 0.5682


747/Unknown  197s 256ms/step - loss: 1.1289 - sparse_categorical_accuracy: 0.5683


748/Unknown  197s 257ms/step - loss: 1.1286 - sparse_categorical_accuracy: 0.5684


749/Unknown  198s 257ms/step - loss: 1.1283 - sparse_categorical_accuracy: 0.5685


750/Unknown  198s 257ms/step - loss: 1.1280 - sparse_categorical_accuracy: 0.5686


751/Unknown  198s 257ms/step - loss: 1.1276 - sparse_categorical_accuracy: 0.5687


752/Unknown  199s 257ms/step - loss: 1.1273 - sparse_categorical_accuracy: 0.5689


753/Unknown  199s 257ms/step - loss: 1.1270 - sparse_categorical_accuracy: 0.5690


754/Unknown  199s 257ms/step - loss: 1.1267 - sparse_categorical_accuracy: 0.5691


755/Unknown  200s 257ms/step - loss: 1.1263 - sparse_categorical_accuracy: 0.5692


756/Unknown  200s 257ms/step - loss: 1.1260 - sparse_categorical_accuracy: 0.5693


757/Unknown  200s 257ms/step - loss: 1.1257 - sparse_categorical_accuracy: 0.5694


758/Unknown  201s 257ms/step - loss: 1.1254 - sparse_categorical_accuracy: 0.5695


759/Unknown  201s 257ms/step - loss: 1.1250 - sparse_categorical_accuracy: 0.5696


760/Unknown  201s 257ms/step - loss: 1.1247 - sparse_categorical_accuracy: 0.5697


761/Unknown  201s 257ms/step - loss: 1.1244 - sparse_categorical_accuracy: 0.5698


762/Unknown  202s 257ms/step - loss: 1.1241 - sparse_categorical_accuracy: 0.5699


763/Unknown  202s 257ms/step - loss: 1.1238 - sparse_categorical_accuracy: 0.5700


764/Unknown  202s 257ms/step - loss: 1.1235 - sparse_categorical_accuracy: 0.5701


765/Unknown  202s 257ms/step - loss: 1.1231 - sparse_categorical_accuracy: 0.5702


766/Unknown  203s 257ms/step - loss: 1.1228 - sparse_categorical_accuracy: 0.5703


767/Unknown  203s 257ms/step - loss: 1.1225 - sparse_categorical_accuracy: 0.5704


768/Unknown  203s 257ms/step - loss: 1.1222 - sparse_categorical_accuracy: 0.5705


769/Unknown  203s 257ms/step - loss: 1.1219 - sparse_categorical_accuracy: 0.5706


770/Unknown  204s 257ms/step - loss: 1.1216 - sparse_categorical_accuracy: 0.5707


771/Unknown  204s 257ms/step - loss: 1.1212 - sparse_categorical_accuracy: 0.5708


772/Unknown  204s 257ms/step - loss: 1.1209 - sparse_categorical_accuracy: 0.5709


773/Unknown  204s 257ms/step - loss: 1.1206 - sparse_categorical_accuracy: 0.5710


774/Unknown  205s 257ms/step - loss: 1.1203 - sparse_categorical_accuracy: 0.5711


775/Unknown  205s 257ms/step - loss: 1.1200 - sparse_categorical_accuracy: 0.5712


776/Unknown  205s 257ms/step - loss: 1.1197 - sparse_categorical_accuracy: 0.5713


777/Unknown  205s 257ms/step - loss: 1.1194 - sparse_categorical_accuracy: 0.5714


778/Unknown  206s 257ms/step - loss: 1.1191 - sparse_categorical_accuracy: 0.5715


779/Unknown  206s 257ms/step - loss: 1.1188 - sparse_categorical_accuracy: 0.5716


780/Unknown  206s 257ms/step - loss: 1.1184 - sparse_categorical_accuracy: 0.5717


781/Unknown  207s 258ms/step - loss: 1.1181 - sparse_categorical_accuracy: 0.5718


782/Unknown  207s 258ms/step - loss: 1.1178 - sparse_categorical_accuracy: 0.5719


783/Unknown  207s 258ms/step - loss: 1.1175 - sparse_categorical_accuracy: 0.5720


784/Unknown  208s 258ms/step - loss: 1.1172 - sparse_categorical_accuracy: 0.5721


785/Unknown  208s 258ms/step - loss: 1.1169 - sparse_categorical_accuracy: 0.5722


786/Unknown  208s 258ms/step - loss: 1.1166 - sparse_categorical_accuracy: 0.5723


787/Unknown  209s 258ms/step - loss: 1.1163 - sparse_categorical_accuracy: 0.5724


788/Unknown  209s 258ms/step - loss: 1.1160 - sparse_categorical_accuracy: 0.5725


789/Unknown  209s 258ms/step - loss: 1.1157 - sparse_categorical_accuracy: 0.5726


790/Unknown  209s 258ms/step - loss: 1.1154 - sparse_categorical_accuracy: 0.5727


791/Unknown  210s 258ms/step - loss: 1.1151 - sparse_categorical_accuracy: 0.5728


792/Unknown  210s 258ms/step - loss: 1.1148 - sparse_categorical_accuracy: 0.5729


793/Unknown  210s 258ms/step - loss: 1.1145 - sparse_categorical_accuracy: 0.5730


794/Unknown  210s 258ms/step - loss: 1.1142 - sparse_categorical_accuracy: 0.5731


795/Unknown  211s 258ms/step - loss: 1.1139 - sparse_categorical_accuracy: 0.5732


796/Unknown  211s 258ms/step - loss: 1.1136 - sparse_categorical_accuracy: 0.5733


797/Unknown  211s 258ms/step - loss: 1.1133 - sparse_categorical_accuracy: 0.5734


798/Unknown  211s 258ms/step - loss: 1.1130 - sparse_categorical_accuracy: 0.5735


799/Unknown  212s 258ms/step - loss: 1.1127 - sparse_categorical_accuracy: 0.5736


800/Unknown  212s 258ms/step - loss: 1.1124 - sparse_categorical_accuracy: 0.5737


801/Unknown  212s 258ms/step - loss: 1.1121 - sparse_categorical_accuracy: 0.5738


802/Unknown  212s 258ms/step - loss: 1.1118 - sparse_categorical_accuracy: 0.5739


803/Unknown  213s 258ms/step - loss: 1.1115 - sparse_categorical_accuracy: 0.5740


804/Unknown  213s 258ms/step - loss: 1.1112 - sparse_categorical_accuracy: 0.5741


805/Unknown  213s 258ms/step - loss: 1.1109 - sparse_categorical_accuracy: 0.5742


806/Unknown  214s 258ms/step - loss: 1.1106 - sparse_categorical_accuracy: 0.5743


807/Unknown  214s 258ms/step - loss: 1.1103 - sparse_categorical_accuracy: 0.5744


808/Unknown  214s 258ms/step - loss: 1.1100 - sparse_categorical_accuracy: 0.5745


809/Unknown  215s 258ms/step - loss: 1.1097 - sparse_categorical_accuracy: 0.5746


810/Unknown  215s 259ms/step - loss: 1.1094 - sparse_categorical_accuracy: 0.5747


811/Unknown  215s 259ms/step - loss: 1.1091 - sparse_categorical_accuracy: 0.5747


812/Unknown  215s 259ms/step - loss: 1.1088 - sparse_categorical_accuracy: 0.5748


813/Unknown  216s 259ms/step - loss: 1.1086 - sparse_categorical_accuracy: 0.5749


814/Unknown  216s 259ms/step - loss: 1.1083 - sparse_categorical_accuracy: 0.5750


815/Unknown  216s 259ms/step - loss: 1.1080 - sparse_categorical_accuracy: 0.5751


816/Unknown  217s 259ms/step - loss: 1.1077 - sparse_categorical_accuracy: 0.5752


817/Unknown  217s 259ms/step - loss: 1.1074 - sparse_categorical_accuracy: 0.5753


818/Unknown  217s 259ms/step - loss: 1.1071 - sparse_categorical_accuracy: 0.5754


819/Unknown  217s 259ms/step - loss: 1.1068 - sparse_categorical_accuracy: 0.5755


820/Unknown  218s 259ms/step - loss: 1.1065 - sparse_categorical_accuracy: 0.5756


821/Unknown  218s 259ms/step - loss: 1.1062 - sparse_categorical_accuracy: 0.5757


822/Unknown  218s 259ms/step - loss: 1.1060 - sparse_categorical_accuracy: 0.5758


823/Unknown  219s 259ms/step - loss: 1.1057 - sparse_categorical_accuracy: 0.5759


824/Unknown  219s 259ms/step - loss: 1.1054 - sparse_categorical_accuracy: 0.5760


825/Unknown  219s 259ms/step - loss: 1.1051 - sparse_categorical_accuracy: 0.5761


826/Unknown  219s 259ms/step - loss: 1.1048 - sparse_categorical_accuracy: 0.5762


827/Unknown  220s 259ms/step - loss: 1.1045 - sparse_categorical_accuracy: 0.5762


828/Unknown  220s 259ms/step - loss: 1.1042 - sparse_categorical_accuracy: 0.5763


829/Unknown  220s 259ms/step - loss: 1.1039 - sparse_categorical_accuracy: 0.5764


830/Unknown  221s 259ms/step - loss: 1.1037 - sparse_categorical_accuracy: 0.5765


831/Unknown  221s 259ms/step - loss: 1.1034 - sparse_categorical_accuracy: 0.5766


832/Unknown  221s 259ms/step - loss: 1.1031 - sparse_categorical_accuracy: 0.5767


833/Unknown  222s 259ms/step - loss: 1.1028 - sparse_categorical_accuracy: 0.5768


834/Unknown  222s 259ms/step - loss: 1.1025 - sparse_categorical_accuracy: 0.5769


835/Unknown  222s 259ms/step - loss: 1.1022 - sparse_categorical_accuracy: 0.5770


836/Unknown  222s 259ms/step - loss: 1.1020 - sparse_categorical_accuracy: 0.5771


837/Unknown  223s 259ms/step - loss: 1.1017 - sparse_categorical_accuracy: 0.5772


838/Unknown  223s 259ms/step - loss: 1.1014 - sparse_categorical_accuracy: 0.5773


839/Unknown  223s 259ms/step - loss: 1.1011 - sparse_categorical_accuracy: 0.5773


840/Unknown  223s 259ms/step - loss: 1.1008 - sparse_categorical_accuracy: 0.5774


841/Unknown  224s 259ms/step - loss: 1.1006 - sparse_categorical_accuracy: 0.5775


842/Unknown  224s 259ms/step - loss: 1.1003 - sparse_categorical_accuracy: 0.5776


843/Unknown  224s 259ms/step - loss: 1.1000 - sparse_categorical_accuracy: 0.5777


844/Unknown  224s 259ms/step - loss: 1.0997 - sparse_categorical_accuracy: 0.5778


845/Unknown  225s 259ms/step - loss: 1.0995 - sparse_categorical_accuracy: 0.5779


846/Unknown  225s 259ms/step - loss: 1.0992 - sparse_categorical_accuracy: 0.5780


847/Unknown  225s 259ms/step - loss: 1.0989 - sparse_categorical_accuracy: 0.5781


848/Unknown  225s 259ms/step - loss: 1.0986 - sparse_categorical_accuracy: 0.5782


849/Unknown  226s 259ms/step - loss: 1.0984 - sparse_categorical_accuracy: 0.5782


850/Unknown  226s 259ms/step - loss: 1.0981 - sparse_categorical_accuracy: 0.5783


851/Unknown  226s 259ms/step - loss: 1.0978 - sparse_categorical_accuracy: 0.5784


852/Unknown  227s 259ms/step - loss: 1.0975 - sparse_categorical_accuracy: 0.5785


853/Unknown  227s 259ms/step - loss: 1.0973 - sparse_categorical_accuracy: 0.5786


854/Unknown  227s 260ms/step - loss: 1.0970 - sparse_categorical_accuracy: 0.5787


855/Unknown  228s 260ms/step - loss: 1.0967 - sparse_categorical_accuracy: 0.5788


856/Unknown  228s 260ms/step - loss: 1.0964 - sparse_categorical_accuracy: 0.5789


857/Unknown  228s 260ms/step - loss: 1.0962 - sparse_categorical_accuracy: 0.5790


858/Unknown  228s 260ms/step - loss: 1.0959 - sparse_categorical_accuracy: 0.5790


859/Unknown  229s 260ms/step - loss: 1.0956 - sparse_categorical_accuracy: 0.5791


860/Unknown  229s 260ms/step - loss: 1.0954 - sparse_categorical_accuracy: 0.5792


861/Unknown  229s 260ms/step - loss: 1.0951 - sparse_categorical_accuracy: 0.5793


862/Unknown  229s 260ms/step - loss: 1.0948 - sparse_categorical_accuracy: 0.5794


863/Unknown  230s 260ms/step - loss: 1.0945 - sparse_categorical_accuracy: 0.5795


864/Unknown  230s 260ms/step - loss: 1.0943 - sparse_categorical_accuracy: 0.5796


865/Unknown  230s 260ms/step - loss: 1.0940 - sparse_categorical_accuracy: 0.5796


866/Unknown  231s 260ms/step - loss: 1.0937 - sparse_categorical_accuracy: 0.5797


867/Unknown  231s 260ms/step - loss: 1.0935 - sparse_categorical_accuracy: 0.5798


868/Unknown  231s 260ms/step - loss: 1.0932 - sparse_categorical_accuracy: 0.5799


869/Unknown  231s 260ms/step - loss: 1.0929 - sparse_categorical_accuracy: 0.5800


870/Unknown  232s 260ms/step - loss: 1.0927 - sparse_categorical_accuracy: 0.5801


871/Unknown  232s 260ms/step - loss: 1.0924 - sparse_categorical_accuracy: 0.5802


872/Unknown  232s 260ms/step - loss: 1.0921 - sparse_categorical_accuracy: 0.5802


873/Unknown  232s 260ms/step - loss: 1.0919 - sparse_categorical_accuracy: 0.5803


874/Unknown  233s 260ms/step - loss: 1.0916 - sparse_categorical_accuracy: 0.5804


875/Unknown  233s 260ms/step - loss: 1.0913 - sparse_categorical_accuracy: 0.5805


876/Unknown  233s 260ms/step - loss: 1.0911 - sparse_categorical_accuracy: 0.5806


877/Unknown  233s 260ms/step - loss: 1.0908 - sparse_categorical_accuracy: 0.5807


878/Unknown  234s 260ms/step - loss: 1.0906 - sparse_categorical_accuracy: 0.5808


879/Unknown  234s 260ms/step - loss: 1.0903 - sparse_categorical_accuracy: 0.5808


880/Unknown  234s 260ms/step - loss: 1.0900 - sparse_categorical_accuracy: 0.5809


881/Unknown  234s 260ms/step - loss: 1.0898 - sparse_categorical_accuracy: 0.5810


882/Unknown  235s 260ms/step - loss: 1.0895 - sparse_categorical_accuracy: 0.5811


883/Unknown  235s 260ms/step - loss: 1.0893 - sparse_categorical_accuracy: 0.5812


884/Unknown  235s 260ms/step - loss: 1.0890 - sparse_categorical_accuracy: 0.5813


885/Unknown  235s 260ms/step - loss: 1.0887 - sparse_categorical_accuracy: 0.5813


886/Unknown  236s 260ms/step - loss: 1.0885 - sparse_categorical_accuracy: 0.5814


887/Unknown  236s 260ms/step - loss: 1.0882 - sparse_categorical_accuracy: 0.5815


888/Unknown  237s 260ms/step - loss: 1.0880 - sparse_categorical_accuracy: 0.5816


889/Unknown  237s 260ms/step - loss: 1.0877 - sparse_categorical_accuracy: 0.5817


890/Unknown  237s 260ms/step - loss: 1.0874 - sparse_categorical_accuracy: 0.5818


891/Unknown  238s 261ms/step - loss: 1.0872 - sparse_categorical_accuracy: 0.5818


892/Unknown  238s 261ms/step - loss: 1.0869 - sparse_categorical_accuracy: 0.5819


893/Unknown  238s 261ms/step - loss: 1.0867 - sparse_categorical_accuracy: 0.5820


894/Unknown  239s 261ms/step - loss: 1.0864 - sparse_categorical_accuracy: 0.5821


895/Unknown  239s 261ms/step - loss: 1.0862 - sparse_categorical_accuracy: 0.5822


896/Unknown  239s 261ms/step - loss: 1.0859 - sparse_categorical_accuracy: 0.5823


897/Unknown  239s 261ms/step - loss: 1.0856 - sparse_categorical_accuracy: 0.5823


898/Unknown  240s 261ms/step - loss: 1.0854 - sparse_categorical_accuracy: 0.5824


899/Unknown  240s 261ms/step - loss: 1.0851 - sparse_categorical_accuracy: 0.5825


900/Unknown  240s 261ms/step - loss: 1.0849 - sparse_categorical_accuracy: 0.5826


901/Unknown  240s 261ms/step - loss: 1.0846 - sparse_categorical_accuracy: 0.5827


902/Unknown  241s 261ms/step - loss: 1.0844 - sparse_categorical_accuracy: 0.5827


903/Unknown  241s 261ms/step - loss: 1.0841 - sparse_categorical_accuracy: 0.5828


904/Unknown  241s 261ms/step - loss: 1.0839 - sparse_categorical_accuracy: 0.5829


905/Unknown  241s 261ms/step - loss: 1.0836 - sparse_categorical_accuracy: 0.5830


906/Unknown  242s 261ms/step - loss: 1.0834 - sparse_categorical_accuracy: 0.5831


907/Unknown  242s 261ms/step - loss: 1.0831 - sparse_categorical_accuracy: 0.5832


908/Unknown  242s 261ms/step - loss: 1.0829 - sparse_categorical_accuracy: 0.5832


909/Unknown  243s 261ms/step - loss: 1.0826 - sparse_categorical_accuracy: 0.5833


910/Unknown  243s 261ms/step - loss: 1.0824 - sparse_categorical_accuracy: 0.5834


911/Unknown  243s 261ms/step - loss: 1.0821 - sparse_categorical_accuracy: 0.5835


912/Unknown  243s 261ms/step - loss: 1.0819 - sparse_categorical_accuracy: 0.5836


913/Unknown  244s 261ms/step - loss: 1.0816 - sparse_categorical_accuracy: 0.5836


914/Unknown  244s 261ms/step - loss: 1.0814 - sparse_categorical_accuracy: 0.5837


915/Unknown  244s 261ms/step - loss: 1.0811 - sparse_categorical_accuracy: 0.5838


916/Unknown  244s 261ms/step - loss: 1.0809 - sparse_categorical_accuracy: 0.5839


917/Unknown  245s 261ms/step - loss: 1.0806 - sparse_categorical_accuracy: 0.5839


918/Unknown  245s 261ms/step - loss: 1.0804 - sparse_categorical_accuracy: 0.5840


919/Unknown  245s 261ms/step - loss: 1.0801 - sparse_categorical_accuracy: 0.5841


920/Unknown  246s 261ms/step - loss: 1.0799 - sparse_categorical_accuracy: 0.5842


921/Unknown  246s 261ms/step - loss: 1.0797 - sparse_categorical_accuracy: 0.5843


922/Unknown  246s 261ms/step - loss: 1.0794 - sparse_categorical_accuracy: 0.5843


923/Unknown  247s 261ms/step - loss: 1.0792 - sparse_categorical_accuracy: 0.5844


924/Unknown  247s 261ms/step - loss: 1.0789 - sparse_categorical_accuracy: 0.5845


925/Unknown  247s 261ms/step - loss: 1.0787 - sparse_categorical_accuracy: 0.5846


926/Unknown  248s 261ms/step - loss: 1.0784 - sparse_categorical_accuracy: 0.5847


927/Unknown  248s 261ms/step - loss: 1.0782 - sparse_categorical_accuracy: 0.5847


928/Unknown  248s 261ms/step - loss: 1.0780 - sparse_categorical_accuracy: 0.5848


929/Unknown  248s 261ms/step - loss: 1.0777 - sparse_categorical_accuracy: 0.5849


930/Unknown  249s 261ms/step - loss: 1.0775 - sparse_categorical_accuracy: 0.5850


931/Unknown  249s 261ms/step - loss: 1.0772 - sparse_categorical_accuracy: 0.5850


932/Unknown  249s 261ms/step - loss: 1.0770 - sparse_categorical_accuracy: 0.5851


933/Unknown  250s 262ms/step - loss: 1.0767 - sparse_categorical_accuracy: 0.5852


934/Unknown  250s 262ms/step - loss: 1.0765 - sparse_categorical_accuracy: 0.5853


935/Unknown  250s 262ms/step - loss: 1.0763 - sparse_categorical_accuracy: 0.5854


936/Unknown  250s 262ms/step - loss: 1.0760 - sparse_categorical_accuracy: 0.5854


937/Unknown  251s 262ms/step - loss: 1.0758 - sparse_categorical_accuracy: 0.5855


938/Unknown  251s 262ms/step - loss: 1.0755 - sparse_categorical_accuracy: 0.5856


939/Unknown  251s 262ms/step - loss: 1.0753 - sparse_categorical_accuracy: 0.5857


940/Unknown  252s 262ms/step - loss: 1.0751 - sparse_categorical_accuracy: 0.5857


941/Unknown  252s 262ms/step - loss: 1.0748 - sparse_categorical_accuracy: 0.5858


942/Unknown  252s 262ms/step - loss: 1.0746 - sparse_categorical_accuracy: 0.5859


943/Unknown  252s 262ms/step - loss: 1.0744 - sparse_categorical_accuracy: 0.5860


944/Unknown  253s 262ms/step - loss: 1.0741 - sparse_categorical_accuracy: 0.5860


945/Unknown  253s 262ms/step - loss: 1.0739 - sparse_categorical_accuracy: 0.5861


946/Unknown  253s 262ms/step - loss: 1.0736 - sparse_categorical_accuracy: 0.5862


947/Unknown  253s 262ms/step - loss: 1.0734 - sparse_categorical_accuracy: 0.5863


948/Unknown  254s 262ms/step - loss: 1.0732 - sparse_categorical_accuracy: 0.5863


949/Unknown  254s 262ms/step - loss: 1.0729 - sparse_categorical_accuracy: 0.5864


950/Unknown  254s 262ms/step - loss: 1.0727 - sparse_categorical_accuracy: 0.5865


951/Unknown  254s 262ms/step - loss: 1.0725 - sparse_categorical_accuracy: 0.5866


952/Unknown  255s 262ms/step - loss: 1.0722 - sparse_categorical_accuracy: 0.5866


953/Unknown  255s 262ms/step - loss: 1.0720 - sparse_categorical_accuracy: 0.5867


954/Unknown  255s 262ms/step - loss: 1.0718 - sparse_categorical_accuracy: 0.5868


955/Unknown  255s 262ms/step - loss: 1.0715 - sparse_categorical_accuracy: 0.5869


956/Unknown  256s 262ms/step - loss: 1.0713 - sparse_categorical_accuracy: 0.5869


957/Unknown  256s 262ms/step - loss: 1.0711 - sparse_categorical_accuracy: 0.5870


958/Unknown  256s 262ms/step - loss: 1.0708 - sparse_categorical_accuracy: 0.5871


959/Unknown  256s 262ms/step - loss: 1.0706 - sparse_categorical_accuracy: 0.5872


960/Unknown  257s 262ms/step - loss: 1.0704 - sparse_categorical_accuracy: 0.5872


961/Unknown  257s 262ms/step - loss: 1.0702 - sparse_categorical_accuracy: 0.5873


962/Unknown  257s 262ms/step - loss: 1.0699 - sparse_categorical_accuracy: 0.5874


963/Unknown  258s 262ms/step - loss: 1.0697 - sparse_categorical_accuracy: 0.5875


964/Unknown  258s 262ms/step - loss: 1.0695 - sparse_categorical_accuracy: 0.5875


965/Unknown  258s 262ms/step - loss: 1.0692 - sparse_categorical_accuracy: 0.5876


966/Unknown  259s 262ms/step - loss: 1.0690 - sparse_categorical_accuracy: 0.5877


967/Unknown  259s 262ms/step - loss: 1.0688 - sparse_categorical_accuracy: 0.5878


968/Unknown  259s 262ms/step - loss: 1.0685 - sparse_categorical_accuracy: 0.5878


969/Unknown  259s 262ms/step - loss: 1.0683 - sparse_categorical_accuracy: 0.5879


970/Unknown  260s 262ms/step - loss: 1.0681 - sparse_categorical_accuracy: 0.5880


971/Unknown  260s 262ms/step - loss: 1.0679 - sparse_categorical_accuracy: 0.5880


972/Unknown  260s 262ms/step - loss: 1.0676 - sparse_categorical_accuracy: 0.5881


973/Unknown  261s 262ms/step - loss: 1.0674 - sparse_categorical_accuracy: 0.5882


974/Unknown  261s 262ms/step - loss: 1.0672 - sparse_categorical_accuracy: 0.5883


975/Unknown  261s 262ms/step - loss: 1.0670 - sparse_categorical_accuracy: 0.5883


976/Unknown  261s 262ms/step - loss: 1.0667 - sparse_categorical_accuracy: 0.5884


977/Unknown  262s 262ms/step - loss: 1.0665 - sparse_categorical_accuracy: 0.5885


978/Unknown  262s 262ms/step - loss: 1.0663 - sparse_categorical_accuracy: 0.5886


979/Unknown  262s 262ms/step - loss: 1.0661 - sparse_categorical_accuracy: 0.5886


980/Unknown  263s 262ms/step - loss: 1.0658 - sparse_categorical_accuracy: 0.5887


981/Unknown  263s 262ms/step - loss: 1.0656 - sparse_categorical_accuracy: 0.5888


982/Unknown  263s 262ms/step - loss: 1.0654 - sparse_categorical_accuracy: 0.5888


983/Unknown  263s 262ms/step - loss: 1.0652 - sparse_categorical_accuracy: 0.5889


984/Unknown  264s 262ms/step - loss: 1.0649 - sparse_categorical_accuracy: 0.5890


985/Unknown  264s 262ms/step - loss: 1.0647 - sparse_categorical_accuracy: 0.5891


986/Unknown  264s 262ms/step - loss: 1.0645 - sparse_categorical_accuracy: 0.5891


987/Unknown  264s 262ms/step - loss: 1.0643 - sparse_categorical_accuracy: 0.5892


988/Unknown  265s 262ms/step - loss: 1.0641 - sparse_categorical_accuracy: 0.5893


989/Unknown  265s 262ms/step - loss: 1.0638 - sparse_categorical_accuracy: 0.5893


990/Unknown  265s 262ms/step - loss: 1.0636 - sparse_categorical_accuracy: 0.5894


991/Unknown  265s 262ms/step - loss: 1.0634 - sparse_categorical_accuracy: 0.5895


992/Unknown  266s 262ms/step - loss: 1.0632 - sparse_categorical_accuracy: 0.5896


993/Unknown  266s 262ms/step - loss: 1.0629 - sparse_categorical_accuracy: 0.5896


994/Unknown  266s 262ms/step - loss: 1.0627 - sparse_categorical_accuracy: 0.5897


995/Unknown  266s 262ms/step - loss: 1.0625 - sparse_categorical_accuracy: 0.5898


996/Unknown  267s 262ms/step - loss: 1.0623 - sparse_categorical_accuracy: 0.5898


997/Unknown  267s 262ms/step - loss: 1.0621 - sparse_categorical_accuracy: 0.5899


998/Unknown  267s 262ms/step - loss: 1.0618 - sparse_categorical_accuracy: 0.5900


999/Unknown  267s 262ms/step - loss: 1.0616 - sparse_categorical_accuracy: 0.5900

1000/Unknown 268s 262ms/step - loss: 1.0614 - sparse_categorical_accuracy: 0.5901

1001/Unknown 268s 262ms/step - loss: 1.0612 - sparse_categorical_accuracy: 0.5902

1002/Unknown 268s 262ms/step - loss: 1.0610 - sparse_categorical_accuracy: 0.5903

1003/Unknown 269s 262ms/step - loss: 1.0608 - sparse_categorical_accuracy: 0.5903

1004/Unknown 269s 262ms/step - loss: 1.0605 - sparse_categorical_accuracy: 0.5904

1005/Unknown 269s 262ms/step - loss: 1.0603 - sparse_categorical_accuracy: 0.5905

1006/Unknown 270s 263ms/step - loss: 1.0601 - sparse_categorical_accuracy: 0.5905

1007/Unknown 270s 263ms/step - loss: 1.0599 - sparse_categorical_accuracy: 0.5906

1008/Unknown 270s 263ms/step - loss: 1.0597 - sparse_categorical_accuracy: 0.5907

1009/Unknown 271s 263ms/step - loss: 1.0595 - sparse_categorical_accuracy: 0.5907

1010/Unknown 271s 263ms/step - loss: 1.0592 - sparse_categorical_accuracy: 0.5908

1011/Unknown 271s 263ms/step - loss: 1.0590 - sparse_categorical_accuracy: 0.5909

1012/Unknown 271s 263ms/step - loss: 1.0588 - sparse_categorical_accuracy: 0.5909

1013/Unknown 272s 263ms/step - loss: 1.0586 - sparse_categorical_accuracy: 0.5910

1014/Unknown 272s 263ms/step - loss: 1.0584 - sparse_categorical_accuracy: 0.5911

1015/Unknown 272s 263ms/step - loss: 1.0582 - sparse_categorical_accuracy: 0.5912

1016/Unknown 272s 263ms/step - loss: 1.0580 - sparse_categorical_accuracy: 0.5912

1017/Unknown 273s 263ms/step - loss: 1.0578 - sparse_categorical_accuracy: 0.5913

1018/Unknown 273s 263ms/step - loss: 1.0575 - sparse_categorical_accuracy: 0.5914

1019/Unknown 273s 263ms/step - loss: 1.0573 - sparse_categorical_accuracy: 0.5914

1020/Unknown 273s 263ms/step - loss: 1.0571 - sparse_categorical_accuracy: 0.5915

1021/Unknown 274s 263ms/step - loss: 1.0569 - sparse_categorical_accuracy: 0.5916

1022/Unknown 274s 263ms/step - loss: 1.0567 - sparse_categorical_accuracy: 0.5916

1023/Unknown 274s 263ms/step - loss: 1.0565 - sparse_categorical_accuracy: 0.5917

1024/Unknown 275s 263ms/step - loss: 1.0563 - sparse_categorical_accuracy: 0.5918

1025/Unknown 275s 263ms/step - loss: 1.0561 - sparse_categorical_accuracy: 0.5918

1026/Unknown 275s 263ms/step - loss: 1.0559 - sparse_categorical_accuracy: 0.5919

1027/Unknown 275s 263ms/step - loss: 1.0556 - sparse_categorical_accuracy: 0.5920

1028/Unknown 276s 263ms/step - loss: 1.0554 - sparse_categorical_accuracy: 0.5920

1029/Unknown 276s 263ms/step - loss: 1.0552 - sparse_categorical_accuracy: 0.5921

1030/Unknown 276s 263ms/step - loss: 1.0550 - sparse_categorical_accuracy: 0.5922

1031/Unknown 276s 263ms/step - loss: 1.0548 - sparse_categorical_accuracy: 0.5922

1032/Unknown 277s 263ms/step - loss: 1.0546 - sparse_categorical_accuracy: 0.5923

1033/Unknown 277s 263ms/step - loss: 1.0544 - sparse_categorical_accuracy: 0.5924

1034/Unknown 277s 263ms/step - loss: 1.0542 - sparse_categorical_accuracy: 0.5924

1035/Unknown 278s 263ms/step - loss: 1.0540 - sparse_categorical_accuracy: 0.5925

1036/Unknown 278s 263ms/step - loss: 1.0538 - sparse_categorical_accuracy: 0.5926

1037/Unknown 278s 263ms/step - loss: 1.0536 - sparse_categorical_accuracy: 0.5926

1038/Unknown 278s 263ms/step - loss: 1.0533 - sparse_categorical_accuracy: 0.5927

1039/Unknown 279s 263ms/step - loss: 1.0531 - sparse_categorical_accuracy: 0.5928

1040/Unknown 279s 263ms/step - loss: 1.0529 - sparse_categorical_accuracy: 0.5928

1041/Unknown 279s 263ms/step - loss: 1.0527 - sparse_categorical_accuracy: 0.5929

1042/Unknown 280s 263ms/step - loss: 1.0525 - sparse_categorical_accuracy: 0.5930

1043/Unknown 280s 263ms/step - loss: 1.0523 - sparse_categorical_accuracy: 0.5930

1044/Unknown 280s 263ms/step - loss: 1.0521 - sparse_categorical_accuracy: 0.5931

1045/Unknown 280s 263ms/step - loss: 1.0519 - sparse_categorical_accuracy: 0.5932

1046/Unknown 281s 263ms/step - loss: 1.0517 - sparse_categorical_accuracy: 0.5932

1047/Unknown 281s 263ms/step - loss: 1.0515 - sparse_categorical_accuracy: 0.5933

1048/Unknown 281s 263ms/step - loss: 1.0513 - sparse_categorical_accuracy: 0.5934

1049/Unknown 282s 263ms/step - loss: 1.0511 - sparse_categorical_accuracy: 0.5934

1050/Unknown 282s 263ms/step - loss: 1.0509 - sparse_categorical_accuracy: 0.5935

1051/Unknown 282s 263ms/step - loss: 1.0507 - sparse_categorical_accuracy: 0.5935

1052/Unknown 283s 263ms/step - loss: 1.0505 - sparse_categorical_accuracy: 0.5936

1053/Unknown 283s 263ms/step - loss: 1.0503 - sparse_categorical_accuracy: 0.5937

1054/Unknown 283s 263ms/step - loss: 1.0501 - sparse_categorical_accuracy: 0.5937

1055/Unknown 283s 263ms/step - loss: 1.0499 - sparse_categorical_accuracy: 0.5938

1056/Unknown 284s 263ms/step - loss: 1.0497 - sparse_categorical_accuracy: 0.5939

1057/Unknown 284s 263ms/step - loss: 1.0495 - sparse_categorical_accuracy: 0.5939

1058/Unknown 284s 263ms/step - loss: 1.0493 - sparse_categorical_accuracy: 0.5940

1059/Unknown 285s 263ms/step - loss: 1.0491 - sparse_categorical_accuracy: 0.5941

1060/Unknown 285s 263ms/step - loss: 1.0489 - sparse_categorical_accuracy: 0.5941

1061/Unknown 285s 263ms/step - loss: 1.0487 - sparse_categorical_accuracy: 0.5942

1062/Unknown 285s 263ms/step - loss: 1.0485 - sparse_categorical_accuracy: 0.5943

1063/Unknown 285s 263ms/step - loss: 1.0483 - sparse_categorical_accuracy: 0.5943

1064/Unknown 286s 263ms/step - loss: 1.0481 - sparse_categorical_accuracy: 0.5944

1065/Unknown 286s 263ms/step - loss: 1.0479 - sparse_categorical_accuracy: 0.5944

1066/Unknown 286s 263ms/step - loss: 1.0477 - sparse_categorical_accuracy: 0.5945

1067/Unknown 286s 263ms/step - loss: 1.0475 - sparse_categorical_accuracy: 0.5946

1068/Unknown 287s 263ms/step - loss: 1.0473 - sparse_categorical_accuracy: 0.5946

1069/Unknown 287s 263ms/step - loss: 1.0471 - sparse_categorical_accuracy: 0.5947

1070/Unknown 287s 263ms/step - loss: 1.0469 - sparse_categorical_accuracy: 0.5948

1071/Unknown 287s 263ms/step - loss: 1.0467 - sparse_categorical_accuracy: 0.5948

1072/Unknown 288s 263ms/step - loss: 1.0465 - sparse_categorical_accuracy: 0.5949

1073/Unknown 288s 263ms/step - loss: 1.0463 - sparse_categorical_accuracy: 0.5949

1074/Unknown 288s 263ms/step - loss: 1.0461 - sparse_categorical_accuracy: 0.5950

1075/Unknown 289s 263ms/step - loss: 1.0459 - sparse_categorical_accuracy: 0.5951

1076/Unknown 289s 263ms/step - loss: 1.0457 - sparse_categorical_accuracy: 0.5951

1077/Unknown 289s 263ms/step - loss: 1.0455 - sparse_categorical_accuracy: 0.5952

1078/Unknown 290s 264ms/step - loss: 1.0453 - sparse_categorical_accuracy: 0.5953

1079/Unknown 290s 264ms/step - loss: 1.0451 - sparse_categorical_accuracy: 0.5953

1080/Unknown 290s 264ms/step - loss: 1.0449 - sparse_categorical_accuracy: 0.5954

1081/Unknown 291s 264ms/step - loss: 1.0447 - sparse_categorical_accuracy: 0.5954

1082/Unknown 291s 264ms/step - loss: 1.0445 - sparse_categorical_accuracy: 0.5955

1083/Unknown 291s 264ms/step - loss: 1.0443 - sparse_categorical_accuracy: 0.5956

1084/Unknown 291s 264ms/step - loss: 1.0441 - sparse_categorical_accuracy: 0.5956

1085/Unknown 292s 264ms/step - loss: 1.0439 - sparse_categorical_accuracy: 0.5957

1086/Unknown 292s 264ms/step - loss: 1.0437 - sparse_categorical_accuracy: 0.5957

1087/Unknown 292s 264ms/step - loss: 1.0436 - sparse_categorical_accuracy: 0.5958

1088/Unknown 293s 264ms/step - loss: 1.0434 - sparse_categorical_accuracy: 0.5959

1089/Unknown 293s 264ms/step - loss: 1.0432 - sparse_categorical_accuracy: 0.5959

1090/Unknown 293s 264ms/step - loss: 1.0430 - sparse_categorical_accuracy: 0.5960

1091/Unknown 293s 264ms/step - loss: 1.0428 - sparse_categorical_accuracy: 0.5961

1092/Unknown 294s 264ms/step - loss: 1.0426 - sparse_categorical_accuracy: 0.5961

1093/Unknown 294s 264ms/step - loss: 1.0424 - sparse_categorical_accuracy: 0.5962

1094/Unknown 294s 264ms/step - loss: 1.0422 - sparse_categorical_accuracy: 0.5962

1095/Unknown 294s 264ms/step - loss: 1.0420 - sparse_categorical_accuracy: 0.5963

1096/Unknown 295s 264ms/step - loss: 1.0418 - sparse_categorical_accuracy: 0.5964

1097/Unknown 295s 264ms/step - loss: 1.0416 - sparse_categorical_accuracy: 0.5964

1098/Unknown 295s 264ms/step - loss: 1.0414 - sparse_categorical_accuracy: 0.5965

1099/Unknown 295s 264ms/step - loss: 1.0413 - sparse_categorical_accuracy: 0.5965

1100/Unknown 296s 264ms/step - loss: 1.0411 - sparse_categorical_accuracy: 0.5966

1101/Unknown 296s 264ms/step - loss: 1.0409 - sparse_categorical_accuracy: 0.5967

1102/Unknown 296s 264ms/step - loss: 1.0407 - sparse_categorical_accuracy: 0.5967

1103/Unknown 296s 264ms/step - loss: 1.0405 - sparse_categorical_accuracy: 0.5968

1104/Unknown 297s 264ms/step - loss: 1.0403 - sparse_categorical_accuracy: 0.5968

1105/Unknown 297s 264ms/step - loss: 1.0401 - sparse_categorical_accuracy: 0.5969

1106/Unknown 297s 264ms/step - loss: 1.0399 - sparse_categorical_accuracy: 0.5970

1107/Unknown 298s 264ms/step - loss: 1.0397 - sparse_categorical_accuracy: 0.5970

1108/Unknown 298s 264ms/step - loss: 1.0396 - sparse_categorical_accuracy: 0.5971

1109/Unknown 298s 264ms/step - loss: 1.0394 - sparse_categorical_accuracy: 0.5971

1110/Unknown 299s 264ms/step - loss: 1.0392 - sparse_categorical_accuracy: 0.5972

1111/Unknown 299s 264ms/step - loss: 1.0390 - sparse_categorical_accuracy: 0.5973

1112/Unknown 299s 264ms/step - loss: 1.0388 - sparse_categorical_accuracy: 0.5973

1113/Unknown 299s 264ms/step - loss: 1.0386 - sparse_categorical_accuracy: 0.5974

1114/Unknown 300s 264ms/step - loss: 1.0384 - sparse_categorical_accuracy: 0.5974

1115/Unknown 300s 264ms/step - loss: 1.0382 - sparse_categorical_accuracy: 0.5975

1116/Unknown 300s 264ms/step - loss: 1.0381 - sparse_categorical_accuracy: 0.5976

1117/Unknown 300s 264ms/step - loss: 1.0379 - sparse_categorical_accuracy: 0.5976

1118/Unknown 301s 264ms/step - loss: 1.0377 - sparse_categorical_accuracy: 0.5977

1119/Unknown 301s 264ms/step - loss: 1.0375 - sparse_categorical_accuracy: 0.5977

1120/Unknown 301s 264ms/step - loss: 1.0373 - sparse_categorical_accuracy: 0.5978

1121/Unknown 301s 264ms/step - loss: 1.0371 - sparse_categorical_accuracy: 0.5978

1122/Unknown 302s 264ms/step - loss: 1.0369 - sparse_categorical_accuracy: 0.5979

1123/Unknown 302s 264ms/step - loss: 1.0368 - sparse_categorical_accuracy: 0.5980

1124/Unknown 302s 264ms/step - loss: 1.0366 - sparse_categorical_accuracy: 0.5980

1125/Unknown 302s 264ms/step - loss: 1.0364 - sparse_categorical_accuracy: 0.5981

1126/Unknown 303s 264ms/step - loss: 1.0362 - sparse_categorical_accuracy: 0.5981

1127/Unknown 303s 264ms/step - loss: 1.0360 - sparse_categorical_accuracy: 0.5982

1128/Unknown 303s 264ms/step - loss: 1.0358 - sparse_categorical_accuracy: 0.5983

1129/Unknown 303s 264ms/step - loss: 1.0357 - sparse_categorical_accuracy: 0.5983

1130/Unknown 304s 264ms/step - loss: 1.0355 - sparse_categorical_accuracy: 0.5984

1131/Unknown 304s 264ms/step - loss: 1.0353 - sparse_categorical_accuracy: 0.5984

1132/Unknown 304s 264ms/step - loss: 1.0351 - sparse_categorical_accuracy: 0.5985

1133/Unknown 305s 264ms/step - loss: 1.0349 - sparse_categorical_accuracy: 0.5985

1134/Unknown 305s 264ms/step - loss: 1.0347 - sparse_categorical_accuracy: 0.5986

1135/Unknown 305s 264ms/step - loss: 1.0346 - sparse_categorical_accuracy: 0.5987

1136/Unknown 306s 264ms/step - loss: 1.0344 - sparse_categorical_accuracy: 0.5987

1137/Unknown 306s 264ms/step - loss: 1.0342 - sparse_categorical_accuracy: 0.5988

1138/Unknown 306s 264ms/step - loss: 1.0340 - sparse_categorical_accuracy: 0.5988

1139/Unknown 306s 264ms/step - loss: 1.0338 - sparse_categorical_accuracy: 0.5989

1140/Unknown 307s 264ms/step - loss: 1.0337 - sparse_categorical_accuracy: 0.5990

1141/Unknown 307s 264ms/step - loss: 1.0335 - sparse_categorical_accuracy: 0.5990

1142/Unknown 307s 264ms/step - loss: 1.0333 - sparse_categorical_accuracy: 0.5991

1143/Unknown 308s 264ms/step - loss: 1.0331 - sparse_categorical_accuracy: 0.5991

1144/Unknown 308s 264ms/step - loss: 1.0329 - sparse_categorical_accuracy: 0.5992

1145/Unknown 308s 264ms/step - loss: 1.0328 - sparse_categorical_accuracy: 0.5992

1146/Unknown 308s 264ms/step - loss: 1.0326 - sparse_categorical_accuracy: 0.5993

1147/Unknown 309s 264ms/step - loss: 1.0324 - sparse_categorical_accuracy: 0.5993

1148/Unknown 309s 264ms/step - loss: 1.0322 - sparse_categorical_accuracy: 0.5994

1149/Unknown 309s 264ms/step - loss: 1.0320 - sparse_categorical_accuracy: 0.5995

1150/Unknown 310s 264ms/step - loss: 1.0319 - sparse_categorical_accuracy: 0.5995

1151/Unknown 310s 264ms/step - loss: 1.0317 - sparse_categorical_accuracy: 0.5996

1152/Unknown 310s 264ms/step - loss: 1.0315 - sparse_categorical_accuracy: 0.5996

1153/Unknown 310s 264ms/step - loss: 1.0313 - sparse_categorical_accuracy: 0.5997

1154/Unknown 311s 264ms/step - loss: 1.0311 - sparse_categorical_accuracy: 0.5997

1155/Unknown 311s 264ms/step - loss: 1.0310 - sparse_categorical_accuracy: 0.5998

1156/Unknown 311s 264ms/step - loss: 1.0308 - sparse_categorical_accuracy: 0.5999

1157/Unknown 312s 265ms/step - loss: 1.0306 - sparse_categorical_accuracy: 0.5999

1158/Unknown 312s 265ms/step - loss: 1.0304 - sparse_categorical_accuracy: 0.6000

1159/Unknown 312s 265ms/step - loss: 1.0303 - sparse_categorical_accuracy: 0.6000

1160/Unknown 312s 265ms/step - loss: 1.0301 - sparse_categorical_accuracy: 0.6001

1161/Unknown 313s 265ms/step - loss: 1.0299 - sparse_categorical_accuracy: 0.6001

1162/Unknown 313s 265ms/step - loss: 1.0297 - sparse_categorical_accuracy: 0.6002

1163/Unknown 313s 265ms/step - loss: 1.0296 - sparse_categorical_accuracy: 0.6003

1164/Unknown 314s 265ms/step - loss: 1.0294 - sparse_categorical_accuracy: 0.6003

1165/Unknown 314s 265ms/step - loss: 1.0292 - sparse_categorical_accuracy: 0.6004

1166/Unknown 314s 265ms/step - loss: 1.0290 - sparse_categorical_accuracy: 0.6004

1167/Unknown 314s 265ms/step - loss: 1.0289 - sparse_categorical_accuracy: 0.6005

1168/Unknown 315s 265ms/step - loss: 1.0287 - sparse_categorical_accuracy: 0.6005

1169/Unknown 315s 265ms/step - loss: 1.0285 - sparse_categorical_accuracy: 0.6006

1170/Unknown 315s 265ms/step - loss: 1.0283 - sparse_categorical_accuracy: 0.6006

1171/Unknown 315s 265ms/step - loss: 1.0282 - sparse_categorical_accuracy: 0.6007

1172/Unknown 316s 264ms/step - loss: 1.0280 - sparse_categorical_accuracy: 0.6008

1173/Unknown 316s 264ms/step - loss: 1.0278 - sparse_categorical_accuracy: 0.6008

1174/Unknown 316s 264ms/step - loss: 1.0276 - sparse_categorical_accuracy: 0.6009

1175/Unknown 316s 264ms/step - loss: 1.0275 - sparse_categorical_accuracy: 0.6009

1176/Unknown 316s 264ms/step - loss: 1.0273 - sparse_categorical_accuracy: 0.6010

1177/Unknown 317s 264ms/step - loss: 1.0271 - sparse_categorical_accuracy: 0.6010

1178/Unknown 317s 264ms/step - loss: 1.0269 - sparse_categorical_accuracy: 0.6011

1179/Unknown 317s 264ms/step - loss: 1.0268 - sparse_categorical_accuracy: 0.6011

1180/Unknown 317s 264ms/step - loss: 1.0266 - sparse_categorical_accuracy: 0.6012

1181/Unknown 318s 264ms/step - loss: 1.0264 - sparse_categorical_accuracy: 0.6012

1182/Unknown 318s 264ms/step - loss: 1.0263 - sparse_categorical_accuracy: 0.6013

1183/Unknown 318s 264ms/step - loss: 1.0261 - sparse_categorical_accuracy: 0.6014

1184/Unknown 318s 264ms/step - loss: 1.0259 - sparse_categorical_accuracy: 0.6014

1185/Unknown 319s 264ms/step - loss: 1.0257 - sparse_categorical_accuracy: 0.6015

1186/Unknown 319s 264ms/step - loss: 1.0256 - sparse_categorical_accuracy: 0.6015

1187/Unknown 319s 264ms/step - loss: 1.0254 - sparse_categorical_accuracy: 0.6016

1188/Unknown 319s 264ms/step - loss: 1.0252 - sparse_categorical_accuracy: 0.6016

1189/Unknown 320s 264ms/step - loss: 1.0251 - sparse_categorical_accuracy: 0.6017

1190/Unknown 320s 264ms/step - loss: 1.0249 - sparse_categorical_accuracy: 0.6017

1191/Unknown 320s 264ms/step - loss: 1.0247 - sparse_categorical_accuracy: 0.6018

1192/Unknown 320s 264ms/step - loss: 1.0245 - sparse_categorical_accuracy: 0.6018

1193/Unknown 321s 264ms/step - loss: 1.0244 - sparse_categorical_accuracy: 0.6019

1194/Unknown 321s 264ms/step - loss: 1.0242 - sparse_categorical_accuracy: 0.6019

1195/Unknown 321s 264ms/step - loss: 1.0240 - sparse_categorical_accuracy: 0.6020

1196/Unknown 321s 264ms/step - loss: 1.0239 - sparse_categorical_accuracy: 0.6021

1197/Unknown 322s 264ms/step - loss: 1.0237 - sparse_categorical_accuracy: 0.6021

1198/Unknown 322s 264ms/step - loss: 1.0235 - sparse_categorical_accuracy: 0.6022

1199/Unknown 322s 264ms/step - loss: 1.0234 - sparse_categorical_accuracy: 0.6022

1200/Unknown 322s 264ms/step - loss: 1.0232 - sparse_categorical_accuracy: 0.6023

1201/Unknown 323s 264ms/step - loss: 1.0230 - sparse_categorical_accuracy: 0.6023

1202/Unknown 323s 264ms/step - loss: 1.0229 - sparse_categorical_accuracy: 0.6024

1203/Unknown 323s 264ms/step - loss: 1.0227 - sparse_categorical_accuracy: 0.6024

1204/Unknown 323s 264ms/step - loss: 1.0225 - sparse_categorical_accuracy: 0.6025

1205/Unknown 324s 264ms/step - loss: 1.0224 - sparse_categorical_accuracy: 0.6025

1206/Unknown 324s 264ms/step - loss: 1.0222 - sparse_categorical_accuracy: 0.6026

1207/Unknown 324s 264ms/step - loss: 1.0220 - sparse_categorical_accuracy: 0.6026

1208/Unknown 324s 264ms/step - loss: 1.0219 - sparse_categorical_accuracy: 0.6027

1209/Unknown 325s 264ms/step - loss: 1.0217 - sparse_categorical_accuracy: 0.6027

1210/Unknown 325s 264ms/step - loss: 1.0215 - sparse_categorical_accuracy: 0.6028

1211/Unknown 325s 264ms/step - loss: 1.0214 - sparse_categorical_accuracy: 0.6029

1212/Unknown 326s 264ms/step - loss: 1.0212 - sparse_categorical_accuracy: 0.6029

1213/Unknown 326s 264ms/step - loss: 1.0210 - sparse_categorical_accuracy: 0.6030

1214/Unknown 326s 264ms/step - loss: 1.0209 - sparse_categorical_accuracy: 0.6030

1215/Unknown 327s 264ms/step - loss: 1.0207 - sparse_categorical_accuracy: 0.6031

1216/Unknown 327s 264ms/step - loss: 1.0205 - sparse_categorical_accuracy: 0.6031

1217/Unknown 327s 264ms/step - loss: 1.0204 - sparse_categorical_accuracy: 0.6032

1218/Unknown 327s 264ms/step - loss: 1.0202 - sparse_categorical_accuracy: 0.6032

1219/Unknown 328s 264ms/step - loss: 1.0200 - sparse_categorical_accuracy: 0.6033

1220/Unknown 328s 264ms/step - loss: 1.0199 - sparse_categorical_accuracy: 0.6033

1221/Unknown 328s 264ms/step - loss: 1.0197 - sparse_categorical_accuracy: 0.6034

1222/Unknown 328s 264ms/step - loss: 1.0196 - sparse_categorical_accuracy: 0.6034

1223/Unknown 329s 264ms/step - loss: 1.0194 - sparse_categorical_accuracy: 0.6035

1224/Unknown 329s 264ms/step - loss: 1.0192 - sparse_categorical_accuracy: 0.6035

1225/Unknown 329s 264ms/step - loss: 1.0191 - sparse_categorical_accuracy: 0.6036

1226/Unknown 329s 264ms/step - loss: 1.0189 - sparse_categorical_accuracy: 0.6036

1227/Unknown 330s 264ms/step - loss: 1.0187 - sparse_categorical_accuracy: 0.6037

1228/Unknown 330s 264ms/step - loss: 1.0186 - sparse_categorical_accuracy: 0.6037

1229/Unknown 330s 264ms/step - loss: 1.0184 - sparse_categorical_accuracy: 0.6038

1230/Unknown 330s 264ms/step - loss: 1.0183 - sparse_categorical_accuracy: 0.6038

1231/Unknown 331s 264ms/step - loss: 1.0181 - sparse_categorical_accuracy: 0.6039

1232/Unknown 331s 264ms/step - loss: 1.0179 - sparse_categorical_accuracy: 0.6039

1233/Unknown 331s 264ms/step - loss: 1.0178 - sparse_categorical_accuracy: 0.6040

1234/Unknown 331s 264ms/step - loss: 1.0176 - sparse_categorical_accuracy: 0.6040

1235/Unknown 332s 264ms/step - loss: 1.0174 - sparse_categorical_accuracy: 0.6041

1236/Unknown 332s 264ms/step - loss: 1.0173 - sparse_categorical_accuracy: 0.6041

1237/Unknown 332s 264ms/step - loss: 1.0171 - sparse_categorical_accuracy: 0.6042

1238/Unknown 332s 264ms/step - loss: 1.0170 - sparse_categorical_accuracy: 0.6042

1239/Unknown 333s 264ms/step - loss: 1.0168 - sparse_categorical_accuracy: 0.6043

1240/Unknown 333s 264ms/step - loss: 1.0166 - sparse_categorical_accuracy: 0.6043

1241/Unknown 334s 264ms/step - loss: 1.0165 - sparse_categorical_accuracy: 0.6044

1242/Unknown 334s 264ms/step - loss: 1.0163 - sparse_categorical_accuracy: 0.6044

1243/Unknown 334s 264ms/step - loss: 1.0162 - sparse_categorical_accuracy: 0.6045

1244/Unknown 335s 265ms/step - loss: 1.0160 - sparse_categorical_accuracy: 0.6045

1245/Unknown 335s 265ms/step - loss: 1.0158 - sparse_categorical_accuracy: 0.6046

1246/Unknown 335s 265ms/step - loss: 1.0157 - sparse_categorical_accuracy: 0.6046

1247/Unknown 335s 265ms/step - loss: 1.0155 - sparse_categorical_accuracy: 0.6047

1248/Unknown 336s 265ms/step - loss: 1.0154 - sparse_categorical_accuracy: 0.6048

1249/Unknown 336s 265ms/step - loss: 1.0152 - sparse_categorical_accuracy: 0.6048

1250/Unknown 336s 265ms/step - loss: 1.0150 - sparse_categorical_accuracy: 0.6049

1251/Unknown 337s 265ms/step - loss: 1.0149 - sparse_categorical_accuracy: 0.6049

1252/Unknown 337s 265ms/step - loss: 1.0147 - sparse_categorical_accuracy: 0.6050

1253/Unknown 337s 265ms/step - loss: 1.0146 - sparse_categorical_accuracy: 0.6050

1254/Unknown 337s 265ms/step - loss: 1.0144 - sparse_categorical_accuracy: 0.6051

1255/Unknown 338s 265ms/step - loss: 1.0143 - sparse_categorical_accuracy: 0.6051

1256/Unknown 338s 265ms/step - loss: 1.0141 - sparse_categorical_accuracy: 0.6052

1257/Unknown 338s 264ms/step - loss: 1.0139 - sparse_categorical_accuracy: 0.6052

1258/Unknown 338s 264ms/step - loss: 1.0138 - sparse_categorical_accuracy: 0.6053

1259/Unknown 338s 264ms/step - loss: 1.0136 - sparse_categorical_accuracy: 0.6053

1260/Unknown 339s 264ms/step - loss: 1.0135 - sparse_categorical_accuracy: 0.6054

1261/Unknown 339s 264ms/step - loss: 1.0133 - sparse_categorical_accuracy: 0.6054

1262/Unknown 339s 264ms/step - loss: 1.0132 - sparse_categorical_accuracy: 0.6055

1263/Unknown 339s 264ms/step - loss: 1.0130 - sparse_categorical_accuracy: 0.6055

1264/Unknown 340s 264ms/step - loss: 1.0128 - sparse_categorical_accuracy: 0.6055

1265/Unknown 340s 264ms/step - loss: 1.0127 - sparse_categorical_accuracy: 0.6056

1266/Unknown 340s 264ms/step - loss: 1.0125 - sparse_categorical_accuracy: 0.6056

1267/Unknown 340s 264ms/step - loss: 1.0124 - sparse_categorical_accuracy: 0.6057

1268/Unknown 341s 264ms/step - loss: 1.0122 - sparse_categorical_accuracy: 0.6057

1269/Unknown 341s 264ms/step - loss: 1.0121 - sparse_categorical_accuracy: 0.6058

1270/Unknown 341s 264ms/step - loss: 1.0119 - sparse_categorical_accuracy: 0.6058

1271/Unknown 341s 264ms/step - loss: 1.0118 - sparse_categorical_accuracy: 0.6059

1272/Unknown 342s 264ms/step - loss: 1.0116 - sparse_categorical_accuracy: 0.6059

1273/Unknown 342s 264ms/step - loss: 1.0114 - sparse_categorical_accuracy: 0.6060

1274/Unknown 342s 264ms/step - loss: 1.0113 - sparse_categorical_accuracy: 0.6060

1275/Unknown 342s 264ms/step - loss: 1.0111 - sparse_categorical_accuracy: 0.6061

1276/Unknown 343s 264ms/step - loss: 1.0110 - sparse_categorical_accuracy: 0.6061

1277/Unknown 343s 264ms/step - loss: 1.0108 - sparse_categorical_accuracy: 0.6062

1278/Unknown 343s 264ms/step - loss: 1.0107 - sparse_categorical_accuracy: 0.6062

1279/Unknown 344s 264ms/step - loss: 1.0105 - sparse_categorical_accuracy: 0.6063

1280/Unknown 344s 264ms/step - loss: 1.0104 - sparse_categorical_accuracy: 0.6063

1281/Unknown 344s 264ms/step - loss: 1.0102 - sparse_categorical_accuracy: 0.6064

1282/Unknown 345s 264ms/step - loss: 1.0101 - sparse_categorical_accuracy: 0.6064

1283/Unknown 345s 264ms/step - loss: 1.0099 - sparse_categorical_accuracy: 0.6065

1284/Unknown 345s 264ms/step - loss: 1.0098 - sparse_categorical_accuracy: 0.6065

1285/Unknown 345s 265ms/step - loss: 1.0096 - sparse_categorical_accuracy: 0.6066

1286/Unknown 346s 265ms/step - loss: 1.0095 - sparse_categorical_accuracy: 0.6066

1287/Unknown 346s 265ms/step - loss: 1.0093 - sparse_categorical_accuracy: 0.6067

1288/Unknown 346s 265ms/step - loss: 1.0092 - sparse_categorical_accuracy: 0.6067

1289/Unknown 347s 265ms/step - loss: 1.0090 - sparse_categorical_accuracy: 0.6068

1290/Unknown 347s 265ms/step - loss: 1.0088 - sparse_categorical_accuracy: 0.6068

1291/Unknown 347s 265ms/step - loss: 1.0087 - sparse_categorical_accuracy: 0.6069

1292/Unknown 347s 265ms/step - loss: 1.0085 - sparse_categorical_accuracy: 0.6069

1293/Unknown 348s 265ms/step - loss: 1.0084 - sparse_categorical_accuracy: 0.6070

1294/Unknown 348s 265ms/step - loss: 1.0082 - sparse_categorical_accuracy: 0.6070

1295/Unknown 348s 265ms/step - loss: 1.0081 - sparse_categorical_accuracy: 0.6071

1296/Unknown 349s 265ms/step - loss: 1.0079 - sparse_categorical_accuracy: 0.6071

1297/Unknown 349s 265ms/step - loss: 1.0078 - sparse_categorical_accuracy: 0.6071

1298/Unknown 349s 265ms/step - loss: 1.0076 - sparse_categorical_accuracy: 0.6072

1299/Unknown 350s 265ms/step - loss: 1.0075 - sparse_categorical_accuracy: 0.6072

1300/Unknown 350s 265ms/step - loss: 1.0073 - sparse_categorical_accuracy: 0.6073

1301/Unknown 350s 265ms/step - loss: 1.0072 - sparse_categorical_accuracy: 0.6073

1302/Unknown 350s 265ms/step - loss: 1.0070 - sparse_categorical_accuracy: 0.6074

1303/Unknown 351s 265ms/step - loss: 1.0069 - sparse_categorical_accuracy: 0.6074

1304/Unknown 351s 265ms/step - loss: 1.0067 - sparse_categorical_accuracy: 0.6075

1305/Unknown 351s 265ms/step - loss: 1.0066 - sparse_categorical_accuracy: 0.6075

1306/Unknown 351s 265ms/step - loss: 1.0064 - sparse_categorical_accuracy: 0.6076

1307/Unknown 352s 265ms/step - loss: 1.0063 - sparse_categorical_accuracy: 0.6076

1308/Unknown 352s 265ms/step - loss: 1.0061 - sparse_categorical_accuracy: 0.6077

1309/Unknown 352s 265ms/step - loss: 1.0060 - sparse_categorical_accuracy: 0.6077

1310/Unknown 353s 265ms/step - loss: 1.0059 - sparse_categorical_accuracy: 0.6078

1311/Unknown 353s 265ms/step - loss: 1.0057 - sparse_categorical_accuracy: 0.6078

1312/Unknown 353s 265ms/step - loss: 1.0056 - sparse_categorical_accuracy: 0.6079

1313/Unknown 354s 265ms/step - loss: 1.0054 - sparse_categorical_accuracy: 0.6079

1314/Unknown 354s 265ms/step - loss: 1.0053 - sparse_categorical_accuracy: 0.6079

1315/Unknown 354s 265ms/step - loss: 1.0051 - sparse_categorical_accuracy: 0.6080

1316/Unknown 354s 265ms/step - loss: 1.0050 - sparse_categorical_accuracy: 0.6080

1317/Unknown 355s 265ms/step - loss: 1.0048 - sparse_categorical_accuracy: 0.6081

1318/Unknown 355s 265ms/step - loss: 1.0047 - sparse_categorical_accuracy: 0.6081

1319/Unknown 355s 265ms/step - loss: 1.0045 - sparse_categorical_accuracy: 0.6082

1320/Unknown 356s 265ms/step - loss: 1.0044 - sparse_categorical_accuracy: 0.6082

1321/Unknown 356s 265ms/step - loss: 1.0042 - sparse_categorical_accuracy: 0.6083

1322/Unknown 356s 265ms/step - loss: 1.0041 - sparse_categorical_accuracy: 0.6083

1323/Unknown 356s 265ms/step - loss: 1.0039 - sparse_categorical_accuracy: 0.6084

1324/Unknown 357s 265ms/step - loss: 1.0038 - sparse_categorical_accuracy: 0.6084

1325/Unknown 357s 265ms/step - loss: 1.0036 - sparse_categorical_accuracy: 0.6085

1326/Unknown 357s 265ms/step - loss: 1.0035 - sparse_categorical_accuracy: 0.6085

1327/Unknown 358s 265ms/step - loss: 1.0034 - sparse_categorical_accuracy: 0.6086

1328/Unknown 358s 265ms/step - loss: 1.0032 - sparse_categorical_accuracy: 0.6086

1329/Unknown 358s 265ms/step - loss: 1.0031 - sparse_categorical_accuracy: 0.6086

1330/Unknown 358s 265ms/step - loss: 1.0029 - sparse_categorical_accuracy: 0.6087

1331/Unknown 359s 265ms/step - loss: 1.0028 - sparse_categorical_accuracy: 0.6087

1332/Unknown 359s 265ms/step - loss: 1.0026 - sparse_categorical_accuracy: 0.6088

1333/Unknown 359s 265ms/step - loss: 1.0025 - sparse_categorical_accuracy: 0.6088

1334/Unknown 359s 265ms/step - loss: 1.0023 - sparse_categorical_accuracy: 0.6089

1335/Unknown 360s 265ms/step - loss: 1.0022 - sparse_categorical_accuracy: 0.6089

1336/Unknown 360s 265ms/step - loss: 1.0021 - sparse_categorical_accuracy: 0.6090

1337/Unknown 360s 265ms/step - loss: 1.0019 - sparse_categorical_accuracy: 0.6090

1338/Unknown 361s 265ms/step - loss: 1.0018 - sparse_categorical_accuracy: 0.6091

1339/Unknown 361s 265ms/step - loss: 1.0016 - sparse_categorical_accuracy: 0.6091

1340/Unknown 361s 265ms/step - loss: 1.0015 - sparse_categorical_accuracy: 0.6091

1341/Unknown 361s 265ms/step - loss: 1.0013 - sparse_categorical_accuracy: 0.6092

1342/Unknown 362s 265ms/step - loss: 1.0012 - sparse_categorical_accuracy: 0.6092

1343/Unknown 362s 265ms/step - loss: 1.0010 - sparse_categorical_accuracy: 0.6093

1344/Unknown 362s 265ms/step - loss: 1.0009 - sparse_categorical_accuracy: 0.6093

1345/Unknown 362s 265ms/step - loss: 1.0008 - sparse_categorical_accuracy: 0.6094

1346/Unknown 363s 265ms/step - loss: 1.0006 - sparse_categorical_accuracy: 0.6094

1347/Unknown 363s 265ms/step - loss: 1.0005 - sparse_categorical_accuracy: 0.6095

1348/Unknown 363s 265ms/step - loss: 1.0003 - sparse_categorical_accuracy: 0.6095

1349/Unknown 364s 265ms/step - loss: 1.0002 - sparse_categorical_accuracy: 0.6096

1350/Unknown 364s 265ms/step - loss: 1.0000 - sparse_categorical_accuracy: 0.6096

1351/Unknown 364s 265ms/step - loss: 0.9999 - sparse_categorical_accuracy: 0.6096

1352/Unknown 364s 265ms/step - loss: 0.9998 - sparse_categorical_accuracy: 0.6097

1353/Unknown 365s 265ms/step - loss: 0.9996 - sparse_categorical_accuracy: 0.6097

1354/Unknown 365s 265ms/step - loss: 0.9995 - sparse_categorical_accuracy: 0.6098

1355/Unknown 365s 265ms/step - loss: 0.9993 - sparse_categorical_accuracy: 0.6098

1356/Unknown 366s 266ms/step - loss: 0.9992 - sparse_categorical_accuracy: 0.6099

1357/Unknown 366s 266ms/step - loss: 0.9991 - sparse_categorical_accuracy: 0.6099

1358/Unknown 366s 266ms/step - loss: 0.9989 - sparse_categorical_accuracy: 0.6100

1359/Unknown 366s 266ms/step - loss: 0.9988 - sparse_categorical_accuracy: 0.6100

1360/Unknown 367s 266ms/step - loss: 0.9986 - sparse_categorical_accuracy: 0.6100

1361/Unknown 367s 266ms/step - loss: 0.9985 - sparse_categorical_accuracy: 0.6101

1362/Unknown 367s 265ms/step - loss: 0.9984 - sparse_categorical_accuracy: 0.6101

1363/Unknown 367s 265ms/step - loss: 0.9982 - sparse_categorical_accuracy: 0.6102

1364/Unknown 368s 266ms/step - loss: 0.9981 - sparse_categorical_accuracy: 0.6102

1365/Unknown 368s 266ms/step - loss: 0.9979 - sparse_categorical_accuracy: 0.6103

1366/Unknown 368s 266ms/step - loss: 0.9978 - sparse_categorical_accuracy: 0.6103

1367/Unknown 369s 266ms/step - loss: 0.9977 - sparse_categorical_accuracy: 0.6104

1368/Unknown 369s 266ms/step - loss: 0.9975 - sparse_categorical_accuracy: 0.6104

1369/Unknown 369s 266ms/step - loss: 0.9974 - sparse_categorical_accuracy: 0.6104

1370/Unknown 369s 266ms/step - loss: 0.9972 - sparse_categorical_accuracy: 0.6105

1371/Unknown 370s 266ms/step - loss: 0.9971 - sparse_categorical_accuracy: 0.6105

1372/Unknown 370s 266ms/step - loss: 0.9970 - sparse_categorical_accuracy: 0.6106

1373/Unknown 370s 266ms/step - loss: 0.9968 - sparse_categorical_accuracy: 0.6106

1374/Unknown 371s 266ms/step - loss: 0.9967 - sparse_categorical_accuracy: 0.6107

1375/Unknown 371s 266ms/step - loss: 0.9965 - sparse_categorical_accuracy: 0.6107

1376/Unknown 371s 266ms/step - loss: 0.9964 - sparse_categorical_accuracy: 0.6107

1377/Unknown 372s 266ms/step - loss: 0.9963 - sparse_categorical_accuracy: 0.6108

1378/Unknown 372s 266ms/step - loss: 0.9961 - sparse_categorical_accuracy: 0.6108

1379/Unknown 372s 266ms/step - loss: 0.9960 - sparse_categorical_accuracy: 0.6109

1380/Unknown 372s 266ms/step - loss: 0.9959 - sparse_categorical_accuracy: 0.6109

1381/Unknown 373s 266ms/step - loss: 0.9957 - sparse_categorical_accuracy: 0.6110

1382/Unknown 373s 266ms/step - loss: 0.9956 - sparse_categorical_accuracy: 0.6110

1383/Unknown 373s 266ms/step - loss: 0.9954 - sparse_categorical_accuracy: 0.6111

1384/Unknown 374s 266ms/step - loss: 0.9953 - sparse_categorical_accuracy: 0.6111

1385/Unknown 374s 266ms/step - loss: 0.9952 - sparse_categorical_accuracy: 0.6111

1386/Unknown 374s 266ms/step - loss: 0.9950 - sparse_categorical_accuracy: 0.6112

1387/Unknown 374s 266ms/step - loss: 0.9949 - sparse_categorical_accuracy: 0.6112

1388/Unknown 375s 266ms/step - loss: 0.9948 - sparse_categorical_accuracy: 0.6113

1389/Unknown 375s 266ms/step - loss: 0.9946 - sparse_categorical_accuracy: 0.6113

1390/Unknown 375s 266ms/step - loss: 0.9945 - sparse_categorical_accuracy: 0.6114

1391/Unknown 376s 266ms/step - loss: 0.9943 - sparse_categorical_accuracy: 0.6114

1392/Unknown 376s 266ms/step - loss: 0.9942 - sparse_categorical_accuracy: 0.6114

1393/Unknown 376s 266ms/step - loss: 0.9941 - sparse_categorical_accuracy: 0.6115

1394/Unknown 377s 266ms/step - loss: 0.9939 - sparse_categorical_accuracy: 0.6115

1395/Unknown 377s 266ms/step - loss: 0.9938 - sparse_categorical_accuracy: 0.6116

1396/Unknown 377s 266ms/step - loss: 0.9937 - sparse_categorical_accuracy: 0.6116

1397/Unknown 378s 266ms/step - loss: 0.9935 - sparse_categorical_accuracy: 0.6117

1398/Unknown 378s 266ms/step - loss: 0.9934 - sparse_categorical_accuracy: 0.6117

1399/Unknown 378s 266ms/step - loss: 0.9933 - sparse_categorical_accuracy: 0.6117

1400/Unknown 378s 266ms/step - loss: 0.9931 - sparse_categorical_accuracy: 0.6118

1401/Unknown 379s 266ms/step - loss: 0.9930 - sparse_categorical_accuracy: 0.6118

1402/Unknown 379s 266ms/step - loss: 0.9929 - sparse_categorical_accuracy: 0.6119

1403/Unknown 379s 266ms/step - loss: 0.9927 - sparse_categorical_accuracy: 0.6119

1404/Unknown 379s 266ms/step - loss: 0.9926 - sparse_categorical_accuracy: 0.6120

1405/Unknown 380s 266ms/step - loss: 0.9925 - sparse_categorical_accuracy: 0.6120

1406/Unknown 380s 266ms/step - loss: 0.9923 - sparse_categorical_accuracy: 0.6120

1407/Unknown 380s 266ms/step - loss: 0.9922 - sparse_categorical_accuracy: 0.6121

1408/Unknown 380s 266ms/step - loss: 0.9921 - sparse_categorical_accuracy: 0.6121

1409/Unknown 381s 266ms/step - loss: 0.9919 - sparse_categorical_accuracy: 0.6122

1410/Unknown 381s 266ms/step - loss: 0.9918 - sparse_categorical_accuracy: 0.6122

1411/Unknown 381s 266ms/step - loss: 0.9917 - sparse_categorical_accuracy: 0.6122

1412/Unknown 382s 266ms/step - loss: 0.9915 - sparse_categorical_accuracy: 0.6123

1413/Unknown 382s 266ms/step - loss: 0.9914 - sparse_categorical_accuracy: 0.6123

1414/Unknown 382s 266ms/step - loss: 0.9913 - sparse_categorical_accuracy: 0.6124

1415/Unknown 382s 266ms/step - loss: 0.9911 - sparse_categorical_accuracy: 0.6124

1416/Unknown 383s 266ms/step - loss: 0.9910 - sparse_categorical_accuracy: 0.6125

1417/Unknown 383s 266ms/step - loss: 0.9909 - sparse_categorical_accuracy: 0.6125

1418/Unknown 383s 266ms/step - loss: 0.9907 - sparse_categorical_accuracy: 0.6125

1419/Unknown 384s 266ms/step - loss: 0.9906 - sparse_categorical_accuracy: 0.6126

1420/Unknown 384s 267ms/step - loss: 0.9905 - sparse_categorical_accuracy: 0.6126

1421/Unknown 384s 267ms/step - loss: 0.9903 - sparse_categorical_accuracy: 0.6127

1422/Unknown 385s 267ms/step - loss: 0.9902 - sparse_categorical_accuracy: 0.6127

1423/Unknown 385s 267ms/step - loss: 0.9901 - sparse_categorical_accuracy: 0.6127

1424/Unknown 386s 267ms/step - loss: 0.9899 - sparse_categorical_accuracy: 0.6128

1425/Unknown 386s 267ms/step - loss: 0.9898 - sparse_categorical_accuracy: 0.6128

1426/Unknown 386s 267ms/step - loss: 0.9897 - sparse_categorical_accuracy: 0.6129

1427/Unknown 386s 267ms/step - loss: 0.9895 - sparse_categorical_accuracy: 0.6129

1428/Unknown 387s 267ms/step - loss: 0.9894 - sparse_categorical_accuracy: 0.6130

1429/Unknown 387s 267ms/step - loss: 0.9893 - sparse_categorical_accuracy: 0.6130

1430/Unknown 387s 267ms/step - loss: 0.9891 - sparse_categorical_accuracy: 0.6130

1431/Unknown 388s 267ms/step - loss: 0.9890 - sparse_categorical_accuracy: 0.6131

1432/Unknown 388s 267ms/step - loss: 0.9889 - sparse_categorical_accuracy: 0.6131

1433/Unknown 388s 267ms/step - loss: 0.9888 - sparse_categorical_accuracy: 0.6132

1434/Unknown 388s 267ms/step - loss: 0.9886 - sparse_categorical_accuracy: 0.6132

1435/Unknown 389s 267ms/step - loss: 0.9885 - sparse_categorical_accuracy: 0.6132

1436/Unknown 389s 267ms/step - loss: 0.9884 - sparse_categorical_accuracy: 0.6133

1437/Unknown 389s 267ms/step - loss: 0.9882 - sparse_categorical_accuracy: 0.6133

1438/Unknown 390s 267ms/step - loss: 0.9881 - sparse_categorical_accuracy: 0.6134

1439/Unknown 390s 267ms/step - loss: 0.9880 - sparse_categorical_accuracy: 0.6134

1440/Unknown 390s 267ms/step - loss: 0.9878 - sparse_categorical_accuracy: 0.6134

1441/Unknown 391s 267ms/step - loss: 0.9877 - sparse_categorical_accuracy: 0.6135

1442/Unknown 391s 267ms/step - loss: 0.9876 - sparse_categorical_accuracy: 0.6135

1443/Unknown 391s 267ms/step - loss: 0.9875 - sparse_categorical_accuracy: 0.6136

1444/Unknown 391s 267ms/step - loss: 0.9873 - sparse_categorical_accuracy: 0.6136

1445/Unknown 392s 267ms/step - loss: 0.9872 - sparse_categorical_accuracy: 0.6137

1446/Unknown 392s 267ms/step - loss: 0.9871 - sparse_categorical_accuracy: 0.6137

1447/Unknown 392s 267ms/step - loss: 0.9869 - sparse_categorical_accuracy: 0.6137

1448/Unknown 393s 267ms/step - loss: 0.9868 - sparse_categorical_accuracy: 0.6138

1449/Unknown 393s 268ms/step - loss: 0.9867 - sparse_categorical_accuracy: 0.6138

1450/Unknown 394s 268ms/step - loss: 0.9866 - sparse_categorical_accuracy: 0.6139

1451/Unknown 394s 268ms/step - loss: 0.9864 - sparse_categorical_accuracy: 0.6139

1452/Unknown 394s 268ms/step - loss: 0.9863 - sparse_categorical_accuracy: 0.6139

1453/Unknown 395s 268ms/step - loss: 0.9862 - sparse_categorical_accuracy: 0.6140

1454/Unknown 395s 268ms/step - loss: 0.9861 - sparse_categorical_accuracy: 0.6140

1455/Unknown 395s 268ms/step - loss: 0.9859 - sparse_categorical_accuracy: 0.6141

1456/Unknown 396s 268ms/step - loss: 0.9858 - sparse_categorical_accuracy: 0.6141

1457/Unknown 396s 268ms/step - loss: 0.9857 - sparse_categorical_accuracy: 0.6141

1458/Unknown 396s 268ms/step - loss: 0.9855 - sparse_categorical_accuracy: 0.6142

1459/Unknown 396s 268ms/step - loss: 0.9854 - sparse_categorical_accuracy: 0.6142

1460/Unknown 397s 268ms/step - loss: 0.9853 - sparse_categorical_accuracy: 0.6143

1461/Unknown 397s 268ms/step - loss: 0.9852 - sparse_categorical_accuracy: 0.6143

1462/Unknown 397s 268ms/step - loss: 0.9850 - sparse_categorical_accuracy: 0.6143

1463/Unknown 397s 268ms/step - loss: 0.9849 - sparse_categorical_accuracy: 0.6144

1464/Unknown 398s 268ms/step - loss: 0.9848 - sparse_categorical_accuracy: 0.6144

1465/Unknown 398s 268ms/step - loss: 0.9847 - sparse_categorical_accuracy: 0.6145

1466/Unknown 398s 268ms/step - loss: 0.9845 - sparse_categorical_accuracy: 0.6145

1467/Unknown 399s 268ms/step - loss: 0.9844 - sparse_categorical_accuracy: 0.6145

1468/Unknown 399s 268ms/step - loss: 0.9843 - sparse_categorical_accuracy: 0.6146

1469/Unknown 399s 268ms/step - loss: 0.9842 - sparse_categorical_accuracy: 0.6146

1470/Unknown 399s 268ms/step - loss: 0.9840 - sparse_categorical_accuracy: 0.6147

1471/Unknown 400s 268ms/step - loss: 0.9839 - sparse_categorical_accuracy: 0.6147

1472/Unknown 400s 268ms/step - loss: 0.9838 - sparse_categorical_accuracy: 0.6147

1473/Unknown 400s 268ms/step - loss: 0.9837 - sparse_categorical_accuracy: 0.6148

1474/Unknown 401s 268ms/step - loss: 0.9835 - sparse_categorical_accuracy: 0.6148

1475/Unknown 401s 268ms/step - loss: 0.9834 - sparse_categorical_accuracy: 0.6149

1476/Unknown 401s 268ms/step - loss: 0.9833 - sparse_categorical_accuracy: 0.6149

1477/Unknown 401s 268ms/step - loss: 0.9832 - sparse_categorical_accuracy: 0.6149

1478/Unknown 402s 268ms/step - loss: 0.9830 - sparse_categorical_accuracy: 0.6150

1479/Unknown 402s 268ms/step - loss: 0.9829 - sparse_categorical_accuracy: 0.6150

1480/Unknown 402s 268ms/step - loss: 0.9828 - sparse_categorical_accuracy: 0.6150

1481/Unknown 403s 268ms/step - loss: 0.9827 - sparse_categorical_accuracy: 0.6151

1482/Unknown 403s 268ms/step - loss: 0.9825 - sparse_categorical_accuracy: 0.6151

1483/Unknown 403s 268ms/step - loss: 0.9824 - sparse_categorical_accuracy: 0.6152

1484/Unknown 404s 268ms/step - loss: 0.9823 - sparse_categorical_accuracy: 0.6152

1485/Unknown 404s 268ms/step - loss: 0.9822 - sparse_categorical_accuracy: 0.6152

1486/Unknown 404s 268ms/step - loss: 0.9820 - sparse_categorical_accuracy: 0.6153

1487/Unknown 404s 268ms/step - loss: 0.9819 - sparse_categorical_accuracy: 0.6153

1488/Unknown 405s 268ms/step - loss: 0.9818 - sparse_categorical_accuracy: 0.6154

1489/Unknown 405s 268ms/step - loss: 0.9817 - sparse_categorical_accuracy: 0.6154

1490/Unknown 405s 268ms/step - loss: 0.9815 - sparse_categorical_accuracy: 0.6154

1491/Unknown 406s 268ms/step - loss: 0.9814 - sparse_categorical_accuracy: 0.6155

1492/Unknown 406s 268ms/step - loss: 0.9813 - sparse_categorical_accuracy: 0.6155

1493/Unknown 406s 268ms/step - loss: 0.9812 - sparse_categorical_accuracy: 0.6156

1494/Unknown 406s 268ms/step - loss: 0.9810 - sparse_categorical_accuracy: 0.6156

1495/Unknown 407s 268ms/step - loss: 0.9809 - sparse_categorical_accuracy: 0.6156

1496/Unknown 407s 268ms/step - loss: 0.9808 - sparse_categorical_accuracy: 0.6157

1497/Unknown 407s 268ms/step - loss: 0.9807 - sparse_categorical_accuracy: 0.6157

1498/Unknown 408s 268ms/step - loss: 0.9806 - sparse_categorical_accuracy: 0.6157

1499/Unknown 408s 268ms/step - loss: 0.9804 - sparse_categorical_accuracy: 0.6158

1500/Unknown 408s 268ms/step - loss: 0.9803 - sparse_categorical_accuracy: 0.6158

1501/Unknown 408s 268ms/step - loss: 0.9802 - sparse_categorical_accuracy: 0.6159

1502/Unknown 409s 268ms/step - loss: 0.9801 - sparse_categorical_accuracy: 0.6159

1503/Unknown 409s 268ms/step - loss: 0.9800 - sparse_categorical_accuracy: 0.6159

1504/Unknown 409s 268ms/step - loss: 0.9798 - sparse_categorical_accuracy: 0.6160

1505/Unknown 410s 268ms/step - loss: 0.9797 - sparse_categorical_accuracy: 0.6160

1506/Unknown 410s 269ms/step - loss: 0.9796 - sparse_categorical_accuracy: 0.6161

1507/Unknown 410s 269ms/step - loss: 0.9795 - sparse_categorical_accuracy: 0.6161

1508/Unknown 411s 269ms/step - loss: 0.9793 - sparse_categorical_accuracy: 0.6161

1509/Unknown 411s 269ms/step - loss: 0.9792 - sparse_categorical_accuracy: 0.6162

1510/Unknown 411s 269ms/step - loss: 0.9791 - sparse_categorical_accuracy: 0.6162

1511/Unknown 411s 269ms/step - loss: 0.9790 - sparse_categorical_accuracy: 0.6162

1512/Unknown 412s 269ms/step - loss: 0.9789 - sparse_categorical_accuracy: 0.6163

1513/Unknown 412s 269ms/step - loss: 0.9787 - sparse_categorical_accuracy: 0.6163

1514/Unknown 412s 269ms/step - loss: 0.9786 - sparse_categorical_accuracy: 0.6164

1515/Unknown 413s 269ms/step - loss: 0.9785 - sparse_categorical_accuracy: 0.6164

1516/Unknown 413s 269ms/step - loss: 0.9784 - sparse_categorical_accuracy: 0.6164

1517/Unknown 413s 269ms/step - loss: 0.9783 - sparse_categorical_accuracy: 0.6165

1518/Unknown 413s 269ms/step - loss: 0.9781 - sparse_categorical_accuracy: 0.6165

1519/Unknown 414s 269ms/step - loss: 0.9780 - sparse_categorical_accuracy: 0.6166

1520/Unknown 414s 269ms/step - loss: 0.9779 - sparse_categorical_accuracy: 0.6166

1521/Unknown 414s 269ms/step - loss: 0.9778 - sparse_categorical_accuracy: 0.6166

1522/Unknown 415s 269ms/step - loss: 0.9777 - sparse_categorical_accuracy: 0.6167

1523/Unknown 415s 269ms/step - loss: 0.9775 - sparse_categorical_accuracy: 0.6167

1524/Unknown 415s 269ms/step - loss: 0.9774 - sparse_categorical_accuracy: 0.6167

1525/Unknown 415s 269ms/step - loss: 0.9773 - sparse_categorical_accuracy: 0.6168

1526/Unknown 416s 269ms/step - loss: 0.9772 - sparse_categorical_accuracy: 0.6168

1527/Unknown 416s 269ms/step - loss: 0.9771 - sparse_categorical_accuracy: 0.6169

1528/Unknown 416s 269ms/step - loss: 0.9769 - sparse_categorical_accuracy: 0.6169

1529/Unknown 417s 269ms/step - loss: 0.9768 - sparse_categorical_accuracy: 0.6169

1530/Unknown 417s 269ms/step - loss: 0.9767 - sparse_categorical_accuracy: 0.6170

1531/Unknown 417s 269ms/step - loss: 0.9766 - sparse_categorical_accuracy: 0.6170

1532/Unknown 417s 269ms/step - loss: 0.9765 - sparse_categorical_accuracy: 0.6170

1533/Unknown 418s 269ms/step - loss: 0.9764 - sparse_categorical_accuracy: 0.6171

1534/Unknown 418s 269ms/step - loss: 0.9762 - sparse_categorical_accuracy: 0.6171

1535/Unknown 418s 269ms/step - loss: 0.9761 - sparse_categorical_accuracy: 0.6172

1536/Unknown 418s 269ms/step - loss: 0.9760 - sparse_categorical_accuracy: 0.6172

1537/Unknown 419s 269ms/step - loss: 0.9759 - sparse_categorical_accuracy: 0.6172

1538/Unknown 419s 269ms/step - loss: 0.9758 - sparse_categorical_accuracy: 0.6173

1539/Unknown 419s 269ms/step - loss: 0.9756 - sparse_categorical_accuracy: 0.6173

1540/Unknown 420s 269ms/step - loss: 0.9755 - sparse_categorical_accuracy: 0.6173

1541/Unknown 420s 269ms/step - loss: 0.9754 - sparse_categorical_accuracy: 0.6174

1542/Unknown 420s 269ms/step - loss: 0.9753 - sparse_categorical_accuracy: 0.6174

1543/Unknown 420s 269ms/step - loss: 0.9752 - sparse_categorical_accuracy: 0.6174

1544/Unknown 421s 269ms/step - loss: 0.9751 - sparse_categorical_accuracy: 0.6175

1545/Unknown 421s 269ms/step - loss: 0.9749 - sparse_categorical_accuracy: 0.6175

1546/Unknown 421s 269ms/step - loss: 0.9748 - sparse_categorical_accuracy: 0.6176

1547/Unknown 422s 269ms/step - loss: 0.9747 - sparse_categorical_accuracy: 0.6176

1548/Unknown 422s 269ms/step - loss: 0.9746 - sparse_categorical_accuracy: 0.6176

1549/Unknown 422s 269ms/step - loss: 0.9745 - sparse_categorical_accuracy: 0.6177

1550/Unknown 422s 269ms/step - loss: 0.9744 - sparse_categorical_accuracy: 0.6177

1551/Unknown 423s 269ms/step - loss: 0.9742 - sparse_categorical_accuracy: 0.6177

1552/Unknown 423s 269ms/step - loss: 0.9741 - sparse_categorical_accuracy: 0.6178

1553/Unknown 423s 269ms/step - loss: 0.9740 - sparse_categorical_accuracy: 0.6178

1554/Unknown 424s 269ms/step - loss: 0.9739 - sparse_categorical_accuracy: 0.6179

1555/Unknown 424s 269ms/step - loss: 0.9738 - sparse_categorical_accuracy: 0.6179

1556/Unknown 424s 269ms/step - loss: 0.9737 - sparse_categorical_accuracy: 0.6179

1557/Unknown 424s 269ms/step - loss: 0.9736 - sparse_categorical_accuracy: 0.6180

1558/Unknown 425s 269ms/step - loss: 0.9734 - sparse_categorical_accuracy: 0.6180

1559/Unknown 425s 269ms/step - loss: 0.9733 - sparse_categorical_accuracy: 0.6180

1560/Unknown 425s 269ms/step - loss: 0.9732 - sparse_categorical_accuracy: 0.6181

1561/Unknown 426s 269ms/step - loss: 0.9731 - sparse_categorical_accuracy: 0.6181

1562/Unknown 426s 269ms/step - loss: 0.9730 - sparse_categorical_accuracy: 0.6181

1563/Unknown 426s 269ms/step - loss: 0.9729 - sparse_categorical_accuracy: 0.6182

1564/Unknown 427s 269ms/step - loss: 0.9727 - sparse_categorical_accuracy: 0.6182

1565/Unknown 427s 269ms/step - loss: 0.9726 - sparse_categorical_accuracy: 0.6182

1566/Unknown 427s 269ms/step - loss: 0.9725 - sparse_categorical_accuracy: 0.6183

1567/Unknown 427s 269ms/step - loss: 0.9724 - sparse_categorical_accuracy: 0.6183

1568/Unknown 428s 269ms/step - loss: 0.9723 - sparse_categorical_accuracy: 0.6184

1569/Unknown 428s 269ms/step - loss: 0.9722 - sparse_categorical_accuracy: 0.6184

1570/Unknown 428s 269ms/step - loss: 0.9721 - sparse_categorical_accuracy: 0.6184

1571/Unknown 428s 269ms/step - loss: 0.9719 - sparse_categorical_accuracy: 0.6185

1572/Unknown 429s 269ms/step - loss: 0.9718 - sparse_categorical_accuracy: 0.6185

1573/Unknown 429s 269ms/step - loss: 0.9717 - sparse_categorical_accuracy: 0.6185

1574/Unknown 429s 269ms/step - loss: 0.9716 - sparse_categorical_accuracy: 0.6186

1575/Unknown 430s 269ms/step - loss: 0.9715 - sparse_categorical_accuracy: 0.6186

1576/Unknown 430s 269ms/step - loss: 0.9714 - sparse_categorical_accuracy: 0.6186

1577/Unknown 430s 269ms/step - loss: 0.9713 - sparse_categorical_accuracy: 0.6187

1578/Unknown 430s 269ms/step - loss: 0.9712 - sparse_categorical_accuracy: 0.6187

1579/Unknown 431s 269ms/step - loss: 0.9710 - sparse_categorical_accuracy: 0.6188

1580/Unknown 431s 269ms/step - loss: 0.9709 - sparse_categorical_accuracy: 0.6188

1581/Unknown 431s 269ms/step - loss: 0.9708 - sparse_categorical_accuracy: 0.6188

1582/Unknown 432s 269ms/step - loss: 0.9707 - sparse_categorical_accuracy: 0.6189

1583/Unknown 432s 269ms/step - loss: 0.9706 - sparse_categorical_accuracy: 0.6189

1584/Unknown 432s 269ms/step - loss: 0.9705 - sparse_categorical_accuracy: 0.6189

1585/Unknown 433s 269ms/step - loss: 0.9704 - sparse_categorical_accuracy: 0.6190

1586/Unknown 433s 269ms/step - loss: 0.9702 - sparse_categorical_accuracy: 0.6190

1587/Unknown 433s 269ms/step - loss: 0.9701 - sparse_categorical_accuracy: 0.6190

1588/Unknown 433s 269ms/step - loss: 0.9700 - sparse_categorical_accuracy: 0.6191

1589/Unknown 434s 269ms/step - loss: 0.9699 - sparse_categorical_accuracy: 0.6191

1590/Unknown 434s 269ms/step - loss: 0.9698 - sparse_categorical_accuracy: 0.6191

1591/Unknown 434s 269ms/step - loss: 0.9697 - sparse_categorical_accuracy: 0.6192

1592/Unknown 435s 270ms/step - loss: 0.9696 - sparse_categorical_accuracy: 0.6192

1593/Unknown 435s 270ms/step - loss: 0.9695 - sparse_categorical_accuracy: 0.6192

1594/Unknown 435s 270ms/step - loss: 0.9694 - sparse_categorical_accuracy: 0.6193

1595/Unknown 435s 270ms/step - loss: 0.9692 - sparse_categorical_accuracy: 0.6193

1596/Unknown 436s 270ms/step - loss: 0.9691 - sparse_categorical_accuracy: 0.6194

1597/Unknown 436s 270ms/step - loss: 0.9690 - sparse_categorical_accuracy: 0.6194

1598/Unknown 436s 270ms/step - loss: 0.9689 - sparse_categorical_accuracy: 0.6194

1599/Unknown 437s 270ms/step - loss: 0.9688 - sparse_categorical_accuracy: 0.6195

1600/Unknown 437s 270ms/step - loss: 0.9687 - sparse_categorical_accuracy: 0.6195

1601/Unknown 437s 270ms/step - loss: 0.9686 - sparse_categorical_accuracy: 0.6195

1602/Unknown 437s 270ms/step - loss: 0.9685 - sparse_categorical_accuracy: 0.6196

1603/Unknown 438s 270ms/step - loss: 0.9684 - sparse_categorical_accuracy: 0.6196

1604/Unknown 438s 270ms/step - loss: 0.9682 - sparse_categorical_accuracy: 0.6196

1605/Unknown 438s 270ms/step - loss: 0.9681 - sparse_categorical_accuracy: 0.6197

1606/Unknown 439s 270ms/step - loss: 0.9680 - sparse_categorical_accuracy: 0.6197

1607/Unknown 439s 270ms/step - loss: 0.9679 - sparse_categorical_accuracy: 0.6197

1608/Unknown 439s 270ms/step - loss: 0.9678 - sparse_categorical_accuracy: 0.6198

1609/Unknown 439s 270ms/step - loss: 0.9677 - sparse_categorical_accuracy: 0.6198

1610/Unknown 440s 270ms/step - loss: 0.9676 - sparse_categorical_accuracy: 0.6198

1611/Unknown 440s 270ms/step - loss: 0.9675 - sparse_categorical_accuracy: 0.6199

1612/Unknown 440s 270ms/step - loss: 0.9674 - sparse_categorical_accuracy: 0.6199

1613/Unknown 441s 270ms/step - loss: 0.9673 - sparse_categorical_accuracy: 0.6199

1614/Unknown 441s 270ms/step - loss: 0.9671 - sparse_categorical_accuracy: 0.6200

1615/Unknown 441s 270ms/step - loss: 0.9670 - sparse_categorical_accuracy: 0.6200

1616/Unknown 442s 270ms/step - loss: 0.9669 - sparse_categorical_accuracy: 0.6200

1617/Unknown 442s 270ms/step - loss: 0.9668 - sparse_categorical_accuracy: 0.6201

1618/Unknown 442s 270ms/step - loss: 0.9667 - sparse_categorical_accuracy: 0.6201

1619/Unknown 442s 270ms/step - loss: 0.9666 - sparse_categorical_accuracy: 0.6202

1620/Unknown 443s 270ms/step - loss: 0.9665 - sparse_categorical_accuracy: 0.6202

1621/Unknown 443s 270ms/step - loss: 0.9664 - sparse_categorical_accuracy: 0.6202

1622/Unknown 443s 270ms/step - loss: 0.9663 - sparse_categorical_accuracy: 0.6203

1623/Unknown 444s 270ms/step - loss: 0.9662 - sparse_categorical_accuracy: 0.6203

1624/Unknown 444s 270ms/step - loss: 0.9661 - sparse_categorical_accuracy: 0.6203

1625/Unknown 444s 270ms/step - loss: 0.9659 - sparse_categorical_accuracy: 0.6204

1626/Unknown 445s 270ms/step - loss: 0.9658 - sparse_categorical_accuracy: 0.6204

1627/Unknown 445s 270ms/step - loss: 0.9657 - sparse_categorical_accuracy: 0.6204

1628/Unknown 445s 270ms/step - loss: 0.9656 - sparse_categorical_accuracy: 0.6205

1629/Unknown 446s 270ms/step - loss: 0.9655 - sparse_categorical_accuracy: 0.6205

1630/Unknown 446s 270ms/step - loss: 0.9654 - sparse_categorical_accuracy: 0.6205

1631/Unknown 446s 270ms/step - loss: 0.9653 - sparse_categorical_accuracy: 0.6206

1632/Unknown 447s 270ms/step - loss: 0.9652 - sparse_categorical_accuracy: 0.6206

1633/Unknown 447s 270ms/step - loss: 0.9651 - sparse_categorical_accuracy: 0.6206

1634/Unknown 447s 270ms/step - loss: 0.9650 - sparse_categorical_accuracy: 0.6207

1635/Unknown 448s 271ms/step - loss: 0.9649 - sparse_categorical_accuracy: 0.6207

1636/Unknown 448s 271ms/step - loss: 0.9648 - sparse_categorical_accuracy: 0.6207

1637/Unknown 448s 271ms/step - loss: 0.9646 - sparse_categorical_accuracy: 0.6208

1638/Unknown 449s 271ms/step - loss: 0.9645 - sparse_categorical_accuracy: 0.6208

1639/Unknown 449s 271ms/step - loss: 0.9644 - sparse_categorical_accuracy: 0.6208

1640/Unknown 449s 271ms/step - loss: 0.9643 - sparse_categorical_accuracy: 0.6209

1641/Unknown 450s 271ms/step - loss: 0.9642 - sparse_categorical_accuracy: 0.6209

1642/未知 450秒 271毫秒/步 - loss: 0.9641 - sparse_categorical_accuracy: 0.6209

1643/未知 450秒 271毫秒/步 - loss: 0.9640 - sparse_categorical_accuracy: 0.6210

1644/未知 450秒 271毫秒/步 - loss: 0.9639 - sparse_categorical_accuracy: 0.6210

1645/未知 451秒 271毫秒/步 - loss: 0.9638 - sparse_categorical_accuracy: 0.6210

1646/未知 451秒 271毫秒/步 - loss: 0.9637 - sparse_categorical_accuracy: 0.6211

1647/未知 451秒 271毫秒/步 - loss: 0.9636 - sparse_categorical_accuracy: 0.6211

1648/未知 452秒 271毫秒/步 - loss: 0.9635 - sparse_categorical_accuracy: 0.6211

1649/未知 452秒 271毫秒/步 - loss: 0.9634 - sparse_categorical_accuracy: 0.6212

1650/未知 452秒 271毫秒/步 - loss: 0.9633 - sparse_categorical_accuracy: 0.6212

1651/未知 452秒 271毫秒/步 - loss: 0.9632 - sparse_categorical_accuracy: 0.6212

1652/未知 453秒 271毫秒/步 - loss: 0.9631 - sparse_categorical_accuracy: 0.6213

1653/未知 453秒 271毫秒/步 - loss: 0.9629 - sparse_categorical_accuracy: 0.6213

1654/未知 453秒 271毫秒/步 - loss: 0.9628 - sparse_categorical_accuracy: 0.6213

1655/未知 454秒 271毫秒/步 - loss: 0.9627 - sparse_categorical_accuracy: 0.6214

1656/未知 454秒 271毫秒/步 - loss: 0.9626 - sparse_categorical_accuracy: 0.6214

1657/未知 454秒 271毫秒/步 - loss: 0.9625 - sparse_categorical_accuracy: 0.6214

1658/未知 455秒 271毫秒/步 - loss: 0.9624 - sparse_categorical_accuracy: 0.6215

1659/未知 455秒 271毫秒/步 - loss: 0.9623 - sparse_categorical_accuracy: 0.6215

1660/未知 455秒 271毫秒/步 - loss: 0.9622 - sparse_categorical_accuracy: 0.6215

1661/未知 455秒 271毫秒/步 - loss: 0.9621 - sparse_categorical_accuracy: 0.6216

1662/未知 456秒 271毫秒/步 - loss: 0.9620 - sparse_categorical_accuracy: 0.6216

1663/未知 456秒 271毫秒/步 - loss: 0.9619 - sparse_categorical_accuracy: 0.6216

1664/未知 456秒 271毫秒/步 - loss: 0.9618 - sparse_categorical_accuracy: 0.6217

1665/未知 457秒 271毫秒/步 - loss: 0.9617 - sparse_categorical_accuracy: 0.6217

1666/未知 457秒 271毫秒/步 - loss: 0.9616 - sparse_categorical_accuracy: 0.6217

1667/未知 457秒 271毫秒/步 - loss: 0.9615 - sparse_categorical_accuracy: 0.6218

1668/未知 457秒 271毫秒/步 - loss: 0.9614 - sparse_categorical_accuracy: 0.6218

1669/未知 458秒 271毫秒/步 - loss: 0.9613 - sparse_categorical_accuracy: 0.6218

1670/未知 458秒 271毫秒/步 - loss: 0.9612 - sparse_categorical_accuracy: 0.6219

1671/未知 458秒 271毫秒/步 - loss: 0.9611 - sparse_categorical_accuracy: 0.6219

1672/未知 459秒 271毫秒/步 - loss: 0.9610 - sparse_categorical_accuracy: 0.6219

1673/未知 459秒 271毫秒/步 - loss: 0.9609 - sparse_categorical_accuracy: 0.6220

1674/未知 459秒 271毫秒/步 - loss: 0.9607 - sparse_categorical_accuracy: 0.6220

1675/未知 460秒 271毫秒/步 - loss: 0.9606 - sparse_categorical_accuracy: 0.6220

1676/未知 460秒 271毫秒/步 - loss: 0.9605 - sparse_categorical_accuracy: 0.6221

1677/未知 460秒 271毫秒/步 - loss: 0.9604 - sparse_categorical_accuracy: 0.6221

1678/未知 460秒 271毫秒/步 - loss: 0.9603 - sparse_categorical_accuracy: 0.6221

1679/未知 461秒 271毫秒/步 - loss: 0.9602 - sparse_categorical_accuracy: 0.6222

1680/未知 461秒 271毫秒/步 - loss: 0.9601 - sparse_categorical_accuracy: 0.6222

1681/未知 461秒 271毫秒/步 - loss: 0.9600 - sparse_categorical_accuracy: 0.6222

1682/未知 462秒 271毫秒/步 - loss: 0.9599 - sparse_categorical_accuracy: 0.6223

1683/未知 462秒 271毫秒/步 - loss: 0.9598 - sparse_categorical_accuracy: 0.6223

1684/未知 462秒 271毫秒/步 - loss: 0.9597 - sparse_categorical_accuracy: 0.6223

1685/未知 462秒 271毫秒/步 - loss: 0.9596 - sparse_categorical_accuracy: 0.6224

1686/未知 463秒 271毫秒/步 - loss: 0.9595 - sparse_categorical_accuracy: 0.6224

1687/未知 463秒 271毫秒/步 - loss: 0.9594 - sparse_categorical_accuracy: 0.6224

1688/未知 463秒 271毫秒/步 - loss: 0.9593 - sparse_categorical_accuracy: 0.6224

1689/未知 463秒 271毫秒/步 - loss: 0.9592 - sparse_categorical_accuracy: 0.6225

1690/未知 464秒 271毫秒/步 - loss: 0.9591 - sparse_categorical_accuracy: 0.6225

1691/未知 464秒 271毫秒/步 - loss: 0.9590 - sparse_categorical_accuracy: 0.6225

1692/未知 464秒 271毫秒/步 - loss: 0.9589 - sparse_categorical_accuracy: 0.6226

1693/未知 464秒 271毫秒/步 - loss: 0.9588 - sparse_categorical_accuracy: 0.6226

1694/未知 465秒 271毫秒/步 - loss: 0.9587 - sparse_categorical_accuracy: 0.6226

1695/未知 465秒 271毫秒/步 - loss: 0.9586 - sparse_categorical_accuracy: 0.6227

1696/未知 465秒 271毫秒/步 - loss: 0.9585 - sparse_categorical_accuracy: 0.6227

1697/未知 465秒 271毫秒/步 - loss: 0.9584 - sparse_categorical_accuracy: 0.6227

1698/未知 466秒 271毫秒/步 - loss: 0.9583 - sparse_categorical_accuracy: 0.6228

1699/未知 466秒 271毫秒/步 - loss: 0.9582 - sparse_categorical_accuracy: 0.6228

1700/未知 466秒 271毫秒/步 - loss: 0.9581 - sparse_categorical_accuracy: 0.6228

1701/未知 466秒 271毫秒/步 - loss: 0.9580 - sparse_categorical_accuracy: 0.6229

1702/未知 467秒 271毫秒/步 - loss: 0.9579 - sparse_categorical_accuracy: 0.6229

1703/未知 467秒 271毫秒/步 - loss: 0.9578 - sparse_categorical_accuracy: 0.6229

1704/未知 467秒 271毫秒/步 - loss: 0.9577 - sparse_categorical_accuracy: 0.6230

1705/未知 468秒 271毫秒/步 - loss: 0.9576 - sparse_categorical_accuracy: 0.6230

1706/未知 468秒 271毫秒/步 - loss: 0.9575 - sparse_categorical_accuracy: 0.6230

1707/未知 468秒 271毫秒/步 - loss: 0.9574 - sparse_categorical_accuracy: 0.6231

1708/未知 469秒 271毫秒/步 - loss: 0.9573 - sparse_categorical_accuracy: 0.6231

1709/未知 469秒 271毫秒/步 - loss: 0.9572 - sparse_categorical_accuracy: 0.6231

1710/未知 469秒 271毫秒/步 - loss: 0.9571 - sparse_categorical_accuracy: 0.6232

1711/未知 470秒 271毫秒/步 - loss: 0.9570 - sparse_categorical_accuracy: 0.6232

1712/未知 470秒 271毫秒/步 - loss: 0.9569 - sparse_categorical_accuracy: 0.6232

1713/未知 470秒 271毫秒/步 - loss: 0.9568 - sparse_categorical_accuracy: 0.6232

1714/未知 470秒 271毫秒/步 - loss: 0.9567 - sparse_categorical_accuracy: 0.6233

1715/未知 471秒 271毫秒/步 - loss: 0.9566 - sparse_categorical_accuracy: 0.6233

1716/未知 471秒 271毫秒/步 - loss: 0.9565 - sparse_categorical_accuracy: 0.6233

1717/未知 471秒 271毫秒/步 - loss: 0.9564 - sparse_categorical_accuracy: 0.6234

1718/未知 471秒 271毫秒/步 - loss: 0.9563 - sparse_categorical_accuracy: 0.6234

1719/未知 472秒 271毫秒/步 - loss: 0.9562 - sparse_categorical_accuracy: 0.6234

1720/未知 472秒 271毫秒/步 - loss: 0.9561 - sparse_categorical_accuracy: 0.6235

1721/未知 472秒 271毫秒/步 - loss: 0.9560 - sparse_categorical_accuracy: 0.6235

1722/未知 472秒 271毫秒/步 - loss: 0.9559 - sparse_categorical_accuracy: 0.6235

1723/未知 473秒 271毫秒/步 - loss: 0.9558 - sparse_categorical_accuracy: 0.6236

1724/未知 473秒 271毫秒/步 - loss: 0.9557 - sparse_categorical_accuracy: 0.6236

1725/未知 473秒 271毫秒/步 - loss: 0.9556 - sparse_categorical_accuracy: 0.6236

1726/未知 473秒 271毫秒/步 - loss: 0.9555 - sparse_categorical_accuracy: 0.6237

1727/未知 474秒 271毫秒/步 - loss: 0.9554 - sparse_categorical_accuracy: 0.6237

1728/未知 474秒 271毫秒/步 - loss: 0.9553 - sparse_categorical_accuracy: 0.6237

1729/未知 474秒 271毫秒/步 - loss: 0.9552 - sparse_categorical_accuracy: 0.6237

1730/未知 474秒 271毫秒/步 - loss: 0.9551 - sparse_categorical_accuracy: 0.6238

1731/未知 475秒 271毫秒/步 - loss: 0.9550 - sparse_categorical_accuracy: 0.6238

1732/未知 475秒 271毫秒/步 - loss: 0.9549 - sparse_categorical_accuracy: 0.6238

1733/未知 476秒 271毫秒/步 - loss: 0.9548 - sparse_categorical_accuracy: 0.6239

1734/未知 476秒 271毫秒/步 - loss: 0.9547 - sparse_categorical_accuracy: 0.6239

1735/未知 476秒 271毫秒/步 - loss: 0.9546 - sparse_categorical_accuracy: 0.6239

1736/未知 477秒 271毫秒/步 - loss: 0.9545 - sparse_categorical_accuracy: 0.6240

1737/未知 477秒 271毫秒/步 - loss: 0.9544 - sparse_categorical_accuracy: 0.6240

1738/未知 477秒 271毫秒/步 - loss: 0.9543 - sparse_categorical_accuracy: 0.6240

1739/未知 478秒 272毫秒/步 - loss: 0.9542 - sparse_categorical_accuracy: 0.6241

1740/未知 478秒 272毫秒/步 - loss: 0.9541 - sparse_categorical_accuracy: 0.6241

1741/未知 478秒 272毫秒/步 - loss: 0.9540 - sparse_categorical_accuracy: 0.6241

1742/未知 479秒 272毫秒/步 - loss: 0.9539 - sparse_categorical_accuracy: 0.6242

1743/未知 479秒 272毫秒/步 - loss: 0.9538 - sparse_categorical_accuracy: 0.6242

1744/未知 479秒 272毫秒/步 - loss: 0.9537 - sparse_categorical_accuracy: 0.6242

1745/未知 480秒 272毫秒/步 - loss: 0.9536 - sparse_categorical_accuracy: 0.6242

1746/未知 480秒 272毫秒/步 - loss: 0.9535 - sparse_categorical_accuracy: 0.6243

1747/未知 480秒 272毫秒/步 - loss: 0.9534 - sparse_categorical_accuracy: 0.6243

1748/未知 481秒 272毫秒/步 - loss: 0.9533 - sparse_categorical_accuracy: 0.6243

1749/未知 481秒 272毫秒/步 - loss: 0.9532 - sparse_categorical_accuracy: 0.6244

1750/未知 481秒 272毫秒/步 - loss: 0.9531 - sparse_categorical_accuracy: 0.6244

1751/未知 481秒 272毫秒/步 - loss: 0.9530 - sparse_categorical_accuracy: 0.6244

1752/未知 482秒 272毫秒/步 - loss: 0.9529 - sparse_categorical_accuracy: 0.6245

1753/未知 482秒 272毫秒/步 - loss: 0.9528 - sparse_categorical_accuracy: 0.6245

1754/未知 482秒 272毫秒/步 - loss: 0.9527 - sparse_categorical_accuracy: 0.6245

1755/未知 483秒 272毫秒/步 - loss: 0.9526 - sparse_categorical_accuracy: 0.6246

1756/未知 483秒 272毫秒/步 - loss: 0.9525 - sparse_categorical_accuracy: 0.6246

1757/未知 483秒 272毫秒/步 - loss: 0.9524 - sparse_categorical_accuracy: 0.6246

1758/未知 484秒 272毫秒/步 - loss: 0.9523 - sparse_categorical_accuracy: 0.6246

1759/未知 484秒 272毫秒/步 - loss: 0.9522 - sparse_categorical_accuracy: 0.6247

1760/未知 484秒 272毫秒/步 - loss: 0.9521 - sparse_categorical_accuracy: 0.6247

1761/未知 484秒 272毫秒/步 - loss: 0.9520 - sparse_categorical_accuracy: 0.6247

1762/未知 485秒 272毫秒/步 - loss: 0.9519 - sparse_categorical_accuracy: 0.6248

1763/未知 485秒 272毫秒/步 - loss: 0.9519 - sparse_categorical_accuracy: 0.6248

1764/未知 485秒 272毫秒/步 - loss: 0.9518 - sparse_categorical_accuracy: 0.6248

1765/未知 486秒 272毫秒/步 - loss: 0.9517 - sparse_categorical_accuracy: 0.6249

1766/未知 486秒 272毫秒/步 - loss: 0.9516 - sparse_categorical_accuracy: 0.6249

1767/未知 486秒 272毫秒/步 - loss: 0.9515 - sparse_categorical_accuracy: 0.6249

1768/未知 487秒 272毫秒/步 - loss: 0.9514 - sparse_categorical_accuracy: 0.6249

1769/未知 487秒 272毫秒/步 - loss: 0.9513 - sparse_categorical_accuracy: 0.6250

1770/未知 488秒 272毫秒/步 - loss: 0.9512 - sparse_categorical_accuracy: 0.6250

1771/未知 488秒 272毫秒/步 - loss: 0.9511 - sparse_categorical_accuracy: 0.6250

1772/未知 488秒 272毫秒/步 - loss: 0.9510 - sparse_categorical_accuracy: 0.6251

1773/未知 489秒 272毫秒/步 - loss: 0.9509 - sparse_categorical_accuracy: 0.6251

1774/未知 489秒 273毫秒/步 - loss: 0.9508 - sparse_categorical_accuracy: 0.6251

1775/未知 489秒 273毫秒/步 - loss: 0.9507 - sparse_categorical_accuracy: 0.6252

1776/未知 490秒 273毫秒/步 - loss: 0.9506 - sparse_categorical_accuracy: 0.6252

1777/未知 490秒 273毫秒/步 - loss: 0.9505 - sparse_categorical_accuracy: 0.6252

1778/未知 490秒 273毫秒/步 - loss: 0.9504 - sparse_categorical_accuracy: 0.6252

1779/未知 491秒 273毫秒/步 - loss: 0.9503 - sparse_categorical_accuracy: 0.6253

1780/未知 491秒 273毫秒/步 - loss: 0.9502 - sparse_categorical_accuracy: 0.6253

1781/未知 492秒 273毫秒/步 - loss: 0.9501 - sparse_categorical_accuracy: 0.6253

1782/未知 492秒 273毫秒/步 - loss: 0.9500 - sparse_categorical_accuracy: 0.6254

1783/未知 492秒 273毫秒/步 - loss: 0.9499 - sparse_categorical_accuracy: 0.6254

1784/未知 493秒 273毫秒/步 - loss: 0.9498 - sparse_categorical_accuracy: 0.6254

1785/未知 493秒 273毫秒/步 - loss: 0.9498 - sparse_categorical_accuracy: 0.6255

1786/未知 493秒 273毫秒/步 - loss: 0.9497 - sparse_categorical_accuracy: 0.6255

1787/未知 494秒 273毫秒/步 - loss: 0.9496 - sparse_categorical_accuracy: 0.6255

1788/未知 494秒 273毫秒/步 - loss: 0.9495 - sparse_categorical_accuracy: 0.6255

1789/未知 494秒 273毫秒/步 - loss: 0.9494 - sparse_categorical_accuracy: 0.6256

1790/未知 495秒 273毫秒/步 - loss: 0.9493 - sparse_categorical_accuracy: 0.6256

1791/未知 495秒 273毫秒/步 - loss: 0.9492 - sparse_categorical_accuracy: 0.6256

1792/未知 495秒 273毫秒/步 - loss: 0.9491 - sparse_categorical_accuracy: 0.6257

1793/未知 496秒 273毫秒/步 - loss: 0.9490 - sparse_categorical_accuracy: 0.6257

1794/未知 496秒 273毫秒/步 - loss: 0.9489 - sparse_categorical_accuracy: 0.6257

1795/未知 496秒 273毫秒/步 - loss: 0.9488 - sparse_categorical_accuracy: 0.6258

1796/未知 497秒 273毫秒/步 - loss: 0.9487 - sparse_categorical_accuracy: 0.6258

1797/未知 497秒 274毫秒/步 - loss: 0.9486 - sparse_categorical_accuracy: 0.6258

1798/未知 497秒 274毫秒/步 - loss: 0.9485 - sparse_categorical_accuracy: 0.6258

1799/未知 498秒 274毫秒/步 - loss: 0.9484 - sparse_categorical_accuracy: 0.6259

1800/未知 498秒 274毫秒/步 - loss: 0.9483 - sparse_categorical_accuracy: 0.6259

1801/未知 498秒 274毫秒/步 - loss: 0.9482 - sparse_categorical_accuracy: 0.6259

1802/未知 499秒 274毫秒/步 - loss: 0.9482 - sparse_categorical_accuracy: 0.6260

1803/未知 499秒 274毫秒/步 - loss: 0.9481 - sparse_categorical_accuracy: 0.6260

1804/未知 499秒 274毫秒/步 - loss: 0.9480 - sparse_categorical_accuracy: 0.6260

1805/未知 500秒 274毫秒/步 - loss: 0.9479 - sparse_categorical_accuracy: 0.6260

1806/未知 500秒 274毫秒/步 - loss: 0.9478 - sparse_categorical_accuracy: 0.6261

1807/未知 500秒 274毫秒/步 - loss: 0.9477 - sparse_categorical_accuracy: 0.6261

1808/未知 501秒 274毫秒/步 - loss: 0.9476 - sparse_categorical_accuracy: 0.6261

1809/未知 501秒 274毫秒/步 - loss: 0.9475 - sparse_categorical_accuracy: 0.6262

1810/未知 501秒 274毫秒/步 - loss: 0.9474 - sparse_categorical_accuracy: 0.6262

1811/未知 502秒 274毫秒/步 - loss: 0.9473 - sparse_categorical_accuracy: 0.6262

1812/未知 502秒 274毫秒/步 - loss: 0.9472 - sparse_categorical_accuracy: 0.6263

1813/未知 502秒 274毫秒/步 - loss: 0.9471 - sparse_categorical_accuracy: 0.6263

1814/未知 503秒 274毫秒/步 - loss: 0.9470 - sparse_categorical_accuracy: 0.6263

1815/未知 503秒 274毫秒/步 - loss: 0.9469 - sparse_categorical_accuracy: 0.6263

1816/未知 503秒 274毫秒/步 - loss: 0.9469 - sparse_categorical_accuracy: 0.6264

1817/未知 504秒 274毫秒/步 - loss: 0.9468 - sparse_categorical_accuracy: 0.6264

1818/未知 504秒 274毫秒/步 - loss: 0.9467 - sparse_categorical_accuracy: 0.6264

1819/未知 504秒 274毫秒/步 - loss: 0.9466 - sparse_categorical_accuracy: 0.6265

1820/未知 505秒 274毫秒/步 - loss: 0.9465 - sparse_categorical_accuracy: 0.6265

1821/未知 505秒 274毫秒/步 - loss: 0.9464 - sparse_categorical_accuracy: 0.6265

1822/未知 505秒 274毫秒/步 - loss: 0.9463 - sparse_categorical_accuracy: 0.6265

1823/未知 505秒 274毫秒/步 - loss: 0.9462 - sparse_categorical_accuracy: 0.6266

1824/未知 506秒 274毫秒/步 - loss: 0.9461 - sparse_categorical_accuracy: 0.6266

1825/未知 506秒 274毫秒/步 - loss: 0.9460 - sparse_categorical_accuracy: 0.6266

1826/未知 506秒 274毫秒/步 - loss: 0.9459 - sparse_categorical_accuracy: 0.6267

1827/未知 507秒 274毫秒/步 - loss: 0.9458 - sparse_categorical_accuracy: 0.6267

1828/未知 507秒 274毫秒/步 - loss: 0.9458 - sparse_categorical_accuracy: 0.6267

1829/未知 507秒 274毫秒/步 - loss: 0.9457 - sparse_categorical_accuracy: 0.6267

1830/未知 508秒 274毫秒/步 - loss: 0.9456 - sparse_categorical_accuracy: 0.6268

1831/未知 508秒 274毫秒/步 - loss: 0.9455 - sparse_categorical_accuracy: 0.6268

1832/未知 508秒 274毫秒/步 - loss: 0.9454 - sparse_categorical_accuracy: 0.6268

1833/未知 509秒 274毫秒/步 - loss: 0.9453 - sparse_categorical_accuracy: 0.6269

1834/未知 509秒 274毫秒/步 - loss: 0.9452 - sparse_categorical_accuracy: 0.6269

1835/未知 509秒 275毫秒/步 - loss: 0.9451 - sparse_categorical_accuracy: 0.6269

1836/未知 510秒 275毫秒/步 - loss: 0.9450 - sparse_categorical_accuracy: 0.6269

1837/未知 510秒 275毫秒/步 - loss: 0.9449 - sparse_categorical_accuracy: 0.6270

1838/未知 510秒 275毫秒/步 - loss: 0.9448 - sparse_categorical_accuracy: 0.6270

1839/未知 511秒 275毫秒/步 - loss: 0.9448 - sparse_categorical_accuracy: 0.6270

1840/未知 511秒 275毫秒/步 - loss: 0.9447 - sparse_categorical_accuracy: 0.6271

1841/未知 511秒 275毫秒/步 - loss: 0.9446 - sparse_categorical_accuracy: 0.6271

1842/未知 512秒 275毫秒/步 - loss: 0.9445 - sparse_categorical_accuracy: 0.6271

1843/未知 512秒 275毫秒/步 - loss: 0.9444 - sparse_categorical_accuracy: 0.6271

1844/未知 513秒 275毫秒/步 - loss: 0.9443 - sparse_categorical_accuracy: 0.6272

1845/未知 513秒 275毫秒/步 - loss: 0.9442 - sparse_categorical_accuracy: 0.6272

1846/未知 513秒 275毫秒/步 - loss: 0.9441 - sparse_categorical_accuracy: 0.6272

1847/未知 513秒 275毫秒/步 - loss: 0.9440 - sparse_categorical_accuracy: 0.6273

1848/未知 514秒 275毫秒/步 - loss: 0.9439 - sparse_categorical_accuracy: 0.6273

1849/未知 514秒 275毫秒/步 - loss: 0.9439 - sparse_categorical_accuracy: 0.6273

1850/未知 514秒 275毫秒/步 - loss: 0.9438 - sparse_categorical_accuracy: 0.6273

1851/未知 514秒 275毫秒/步 - loss: 0.9437 - sparse_categorical_accuracy: 0.6274

1852/未知 515秒 275毫秒/步 - loss: 0.9436 - sparse_categorical_accuracy: 0.6274

1853/未知 515秒 275毫秒/步 - loss: 0.9435 - sparse_categorical_accuracy: 0.6274

1854/未知 515秒 275毫秒/步 - loss: 0.9434 - sparse_categorical_accuracy: 0.6275

1855/未知 516秒 275毫秒/步 - loss: 0.9433 - sparse_categorical_accuracy: 0.6275

1856/未知 516秒 275毫秒/步 - loss: 0.9432 - sparse_categorical_accuracy: 0.6275

1857/未知 516秒 275毫秒/步 - loss: 0.9431 - sparse_categorical_accuracy: 0.6275

1858/未知 517秒 275毫秒/步 - loss: 0.9431 - sparse_categorical_accuracy: 0.6276

1859/未知 517秒 275毫秒/步 - loss: 0.9430 - sparse_categorical_accuracy: 0.6276

1860/未知 517秒 275毫秒/步 - loss: 0.9429 - sparse_categorical_accuracy: 0.6276

1861/未知 517秒 275毫秒/步 - loss: 0.9428 - sparse_categorical_accuracy: 0.6277

1862/未知 518秒 275毫秒/步 - loss: 0.9427 - sparse_categorical_accuracy: 0.6277

1863/未知 518秒 275毫秒/步 - loss: 0.9426 - sparse_categorical_accuracy: 0.6277

1864/未知 518秒 275毫秒/步 - loss: 0.9425 - sparse_categorical_accuracy: 0.6277

1865/未知 519秒 275毫秒/步 - loss: 0.9424 - sparse_categorical_accuracy: 0.6278

1865/1865 ━━━━━━━━━━━━━━━━━━━━ 519秒 275毫秒/步 - loss: 0.9423 - sparse_categorical_accuracy: 0.6278

Model training finished

/home/humbulani/tensorflow-env/env/lib/python3.11/site-packages/keras/src/trainers/epoch_iterator.py:151: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
  self._interrupted_warning()

Test accuracy: 71.32%

基线线性模型在测试集上达到了约76%的准确率。

实验 2：Wide & Deep 模型

在第二个实验中，我们创建了一个 Wide & Deep 模型。模型的 wide 部分是一个线性模型，而 deep 部分是一个多层前馈网络。

在模型的 wide 部分使用输入特征的稀疏表示，在模型的 deep 部分使用输入特征的稠密表示。

请注意，每个输入特征以不同的表示形式对模型的两个部分都有贡献。

def create_wide_and_deep_model():
    inputs = create_model_inputs()
    wide = encode_inputs(inputs)
    wide = layers.BatchNormalization()(wide)

    deep = encode_inputs(inputs, use_embedding=True)
    for units in hidden_units:
        deep = layers.Dense(units)(deep)
        deep = layers.BatchNormalization()(deep)
        deep = layers.ReLU()(deep)
        deep = layers.Dropout(dropout_rate)(deep)

    merged = layers.concatenate([wide, deep])
    outputs = layers.Dense(units=NUM_CLASSES, activation="softmax")(merged)
    model = keras.Model(inputs=inputs, outputs=outputs)
    return model


wide_and_deep_model = create_wide_and_deep_model()
keras.utils.plot_model(wide_and_deep_model, show_shapes=True, rankdir="LR")

png

运行它

run_experiment(wide_and_deep_model)

Start training the model...

  1/Unknown  3s 3s/step - loss: 2.0684 - sparse_categorical_accuracy: 0.2566


  2/Unknown  4s 453ms/step - loss: 2.1023 - sparse_categorical_accuracy: 0.2575


  3/Unknown  4s 434ms/step - loss: 2.1031 - sparse_categorical_accuracy: 0.2618


  4/Unknown  5s 456ms/step - loss: 2.1023 - sparse_categorical_accuracy: 0.2648


  5/Unknown  5s 455ms/step - loss: 2.0994 - sparse_categorical_accuracy: 0.2678


  6/Unknown  5s 452ms/step - loss: 2.0958 - sparse_categorical_accuracy: 0.2694


  7/Unknown  6s 455ms/step - loss: 2.0920 - sparse_categorical_accuracy: 0.2710


  8/Unknown  6s 470ms/step - loss: 2.0869 - sparse_categorical_accuracy: 0.2727


  9/Unknown  7s 479ms/step - loss: 2.0817 - sparse_categorical_accuracy: 0.2742


 10/Unknown  7s 481ms/step - loss: 2.0759 - sparse_categorical_accuracy: 0.2760


 11/Unknown  8s 477ms/step - loss: 2.0698 - sparse_categorical_accuracy: 0.2781


 12/Unknown  8s 481ms/step - loss: 2.0635 - sparse_categorical_accuracy: 0.2802


 13/Unknown  9s 476ms/step - loss: 2.0573 - sparse_categorical_accuracy: 0.2821


 14/Unknown  9s 479ms/step - loss: 2.0513 - sparse_categorical_accuracy: 0.2839


 15/Unknown  10s 480ms/step - loss: 2.0452 - sparse_categorical_accuracy: 0.2858


 16/Unknown  10s 481ms/step - loss: 2.0389 - sparse_categorical_accuracy: 0.2877


 17/Unknown  11s 477ms/step - loss: 2.0326 - sparse_categorical_accuracy: 0.2897


 18/Unknown  11s 478ms/step - loss: 2.0264 - sparse_categorical_accuracy: 0.2918


 19/Unknown  12s 477ms/step - loss: 2.0203 - sparse_categorical_accuracy: 0.2938


 20/Unknown  12s 477ms/step - loss: 2.0141 - sparse_categorical_accuracy: 0.2959


 21/Unknown  13s 476ms/step - loss: 2.0081 - sparse_categorical_accuracy: 0.2979


 22/Unknown  13s 473ms/step - loss: 2.0020 - sparse_categorical_accuracy: 0.2998


 23/Unknown  14s 475ms/step - loss: 1.9961 - sparse_categorical_accuracy: 0.3018


 24/Unknown  14s 476ms/step - loss: 1.9903 - sparse_categorical_accuracy: 0.3037


 25/Unknown  15s 477ms/step - loss: 1.9846 - sparse_categorical_accuracy: 0.3054


 26/Unknown  15s 478ms/step - loss: 1.9790 - sparse_categorical_accuracy: 0.3071


 27/Unknown  16s 478ms/step - loss: 1.9735 - sparse_categorical_accuracy: 0.3088


 28/Unknown  16s 477ms/step - loss: 1.9682 - sparse_categorical_accuracy: 0.3103


 29/Unknown  16s 477ms/step - loss: 1.9629 - sparse_categorical_accuracy: 0.3119


 30/Unknown  17s 478ms/step - loss: 1.9575 - sparse_categorical_accuracy: 0.3136


 31/Unknown  17s 478ms/step - loss: 1.9522 - sparse_categorical_accuracy: 0.3152


 32/Unknown  18s 479ms/step - loss: 1.9469 - sparse_categorical_accuracy: 0.3168


 33/Unknown  18s 478ms/step - loss: 1.9417 - sparse_categorical_accuracy: 0.3183


 34/Unknown  19s 479ms/step - loss: 1.9365 - sparse_categorical_accuracy: 0.3199


 35/Unknown  19s 478ms/step - loss: 1.9313 - sparse_categorical_accuracy: 0.3215


 36/Unknown  20s 478ms/step - loss: 1.9262 - sparse_categorical_accuracy: 0.3230


 37/Unknown  20s 476ms/step - loss: 1.9211 - sparse_categorical_accuracy: 0.3246


 38/Unknown  21s 473ms/step - loss: 1.9160 - sparse_categorical_accuracy: 0.3261


 39/Unknown  21s 469ms/step - loss: 1.9111 - sparse_categorical_accuracy: 0.3275


 40/Unknown  21s 466ms/step - loss: 1.9062 - sparse_categorical_accuracy: 0.3290


 41/Unknown  22s 464ms/step - loss: 1.9013 - sparse_categorical_accuracy: 0.3304


 42/Unknown  22s 463ms/step - loss: 1.8965 - sparse_categorical_accuracy: 0.3318


 43/Unknown  23s 461ms/step - loss: 1.8917 - sparse_categorical_accuracy: 0.3332


 44/Unknown  23s 460ms/step - loss: 1.8869 - sparse_categorical_accuracy: 0.3346


 45/Unknown  23s 458ms/step - loss: 1.8822 - sparse_categorical_accuracy: 0.3360


 46/Unknown  24s 457ms/step - loss: 1.8775 - sparse_categorical_accuracy: 0.3373


 47/Unknown  24s 457ms/step - loss: 1.8728 - sparse_categorical_accuracy: 0.3386


 48/Unknown  25s 455ms/step - loss: 1.8682 - sparse_categorical_accuracy: 0.3399


 49/Unknown  25s 455ms/step - loss: 1.8636 - sparse_categorical_accuracy: 0.3412


 50/Unknown  25s 456ms/step - loss: 1.8591 - sparse_categorical_accuracy: 0.3425


 51/Unknown  26s 457ms/step - loss: 1.8546 - sparse_categorical_accuracy: 0.3438


 52/Unknown  26s 458ms/step - loss: 1.8501 - sparse_categorical_accuracy: 0.3450


 53/Unknown  27s 460ms/step - loss: 1.8456 - sparse_categorical_accuracy: 0.3463


 54/Unknown  27s 460ms/step - loss: 1.8412 - sparse_categorical_accuracy: 0.3476


 55/Unknown  28s 460ms/step - loss: 1.8368 - sparse_categorical_accuracy: 0.3488


 56/Unknown  28s 461ms/step - loss: 1.8325 - sparse_categorical_accuracy: 0.3500


 57/Unknown  29s 461ms/step - loss: 1.8282 - sparse_categorical_accuracy: 0.3513


 58/Unknown  29s 461ms/step - loss: 1.8239 - sparse_categorical_accuracy: 0.3525


 59/Unknown  30s 462ms/step - loss: 1.8197 - sparse_categorical_accuracy: 0.3537


 60/Unknown  30s 463ms/step - loss: 1.8154 - sparse_categorical_accuracy: 0.3549


 61/Unknown  31s 464ms/step - loss: 1.8112 - sparse_categorical_accuracy: 0.3561


 62/Unknown  31s 464ms/step - loss: 1.8071 - sparse_categorical_accuracy: 0.3573


 63/Unknown  32s 465ms/step - loss: 1.8030 - sparse_categorical_accuracy: 0.3584


 64/Unknown  32s 465ms/step - loss: 1.7989 - sparse_categorical_accuracy: 0.3595


 65/Unknown  33s 466ms/step - loss: 1.7949 - sparse_categorical_accuracy: 0.3606


 66/Unknown  33s 466ms/step - loss: 1.7908 - sparse_categorical_accuracy: 0.3618


 67/Unknown  34s 467ms/step - loss: 1.7869 - sparse_categorical_accuracy: 0.3628


 68/Unknown  34s 467ms/step - loss: 1.7829 - sparse_categorical_accuracy: 0.3639


 69/Unknown  35s 467ms/step - loss: 1.7790 - sparse_categorical_accuracy: 0.3650


 70/Unknown  35s 468ms/step - loss: 1.7752 - sparse_categorical_accuracy: 0.3661


 71/Unknown  36s 468ms/step - loss: 1.7713 - sparse_categorical_accuracy: 0.3671


 72/Unknown  36s 468ms/step - loss: 1.7675 - sparse_categorical_accuracy: 0.3682


 73/Unknown  37s 468ms/step - loss: 1.7638 - sparse_categorical_accuracy: 0.3692


 74/Unknown  37s 469ms/step - loss: 1.7600 - sparse_categorical_accuracy: 0.3703


 75/Unknown  38s 468ms/step - loss: 1.7563 - sparse_categorical_accuracy: 0.3713


 76/Unknown  38s 468ms/step - loss: 1.7526 - sparse_categorical_accuracy: 0.3723


 77/Unknown  39s 468ms/step - loss: 1.7490 - sparse_categorical_accuracy: 0.3733


 78/Unknown  39s 468ms/step - loss: 1.7453 - sparse_categorical_accuracy: 0.3743


 79/Unknown  40s 468ms/step - loss: 1.7417 - sparse_categorical_accuracy: 0.3753


 80/Unknown  40s 469ms/step - loss: 1.7382 - sparse_categorical_accuracy: 0.3763


 81/Unknown  41s 470ms/step - loss: 1.7346 - sparse_categorical_accuracy: 0.3773


 82/Unknown  41s 470ms/step - loss: 1.7312 - sparse_categorical_accuracy: 0.3783


 83/Unknown  42s 471ms/step - loss: 1.7277 - sparse_categorical_accuracy: 0.3792


 84/Unknown  42s 471ms/step - loss: 1.7243 - sparse_categorical_accuracy: 0.3802


 85/Unknown  43s 471ms/step - loss: 1.7209 - sparse_categorical_accuracy: 0.3811


 86/Unknown  43s 472ms/step - loss: 1.7175 - sparse_categorical_accuracy: 0.3821


 87/Unknown  44s 471ms/step - loss: 1.7142 - sparse_categorical_accuracy: 0.3830


 88/Unknown  44s 472ms/step - loss: 1.7109 - sparse_categorical_accuracy: 0.3839


 89/Unknown  45s 472ms/step - loss: 1.7076 - sparse_categorical_accuracy: 0.3848


 90/Unknown  45s 473ms/step - loss: 1.7043 - sparse_categorical_accuracy: 0.3857


 91/Unknown  46s 473ms/step - loss: 1.7011 - sparse_categorical_accuracy: 0.3866


 92/Unknown  46s 473ms/step - loss: 1.6979 - sparse_categorical_accuracy: 0.3875


 93/Unknown  47s 473ms/step - loss: 1.6947 - sparse_categorical_accuracy: 0.3884


 94/Unknown  47s 474ms/step - loss: 1.6916 - sparse_categorical_accuracy: 0.3893


 95/Unknown  48s 474ms/step - loss: 1.6884 - sparse_categorical_accuracy: 0.3902


 96/Unknown  48s 474ms/step - loss: 1.6853 - sparse_categorical_accuracy: 0.3911


 97/Unknown  49s 475ms/step - loss: 1.6822 - sparse_categorical_accuracy: 0.3920


 98/Unknown  49s 475ms/step - loss: 1.6791 - sparse_categorical_accuracy: 0.3928


 99/Unknown  50s 475ms/step - loss: 1.6761 - sparse_categorical_accuracy: 0.3937


100/Unknown  50s 475ms/step - loss: 1.6731 - sparse_categorical_accuracy: 0.3946


101/Unknown  51s 475ms/step - loss: 1.6700 - sparse_categorical_accuracy: 0.3954


102/Unknown  51s 475ms/step - loss: 1.6671 - sparse_categorical_accuracy: 0.3962


103/Unknown  52s 476ms/step - loss: 1.6641 - sparse_categorical_accuracy: 0.3971


104/Unknown  52s 476ms/step - loss: 1.6612 - sparse_categorical_accuracy: 0.3979


105/Unknown  53s 476ms/step - loss: 1.6582 - sparse_categorical_accuracy: 0.3988


106/Unknown  53s 476ms/step - loss: 1.6553 - sparse_categorical_accuracy: 0.3996


107/Unknown  54s 476ms/step - loss: 1.6525 - sparse_categorical_accuracy: 0.4004


108/Unknown  54s 476ms/step - loss: 1.6496 - sparse_categorical_accuracy: 0.4012


109/Unknown  55s 477ms/step - loss: 1.6468 - sparse_categorical_accuracy: 0.4020


110/Unknown  55s 477ms/step - loss: 1.6440 - sparse_categorical_accuracy: 0.4028


111/Unknown  56s 477ms/step - loss: 1.6412 - sparse_categorical_accuracy: 0.4036


112/Unknown  56s 477ms/step - loss: 1.6385 - sparse_categorical_accuracy: 0.4044


113/Unknown  57s 477ms/step - loss: 1.6357 - sparse_categorical_accuracy: 0.4052


114/Unknown  57s 477ms/step - loss: 1.6330 - sparse_categorical_accuracy: 0.4059


115/Unknown  57s 476ms/step - loss: 1.6303 - sparse_categorical_accuracy: 0.4067


116/Unknown  58s 477ms/step - loss: 1.6276 - sparse_categorical_accuracy: 0.4075


117/Unknown  58s 476ms/step - loss: 1.6249 - sparse_categorical_accuracy: 0.4082


118/Unknown  59s 477ms/step - loss: 1.6223 - sparse_categorical_accuracy: 0.4090


119/Unknown  59s 477ms/step - loss: 1.6196 - sparse_categorical_accuracy: 0.4098


120/Unknown  60s 477ms/step - loss: 1.6170 - sparse_categorical_accuracy: 0.4105


121/Unknown  60s 477ms/step - loss: 1.6144 - sparse_categorical_accuracy: 0.4113


122/Unknown  61s 477ms/step - loss: 1.6118 - sparse_categorical_accuracy: 0.4120


123/Unknown  61s 477ms/step - loss: 1.6093 - sparse_categorical_accuracy: 0.4128


124/Unknown  62s 477ms/step - loss: 1.6067 - sparse_categorical_accuracy: 0.4135


125/Unknown  62s 477ms/step - loss: 1.6042 - sparse_categorical_accuracy: 0.4142


126/Unknown  63s 477ms/step - loss: 1.6017 - sparse_categorical_accuracy: 0.4150


127/Unknown  63s 477ms/step - loss: 1.5991 - sparse_categorical_accuracy: 0.4157


128/Unknown  64s 477ms/step - loss: 1.5967 - sparse_categorical_accuracy: 0.4164


129/Unknown  64s 477ms/step - loss: 1.5942 - sparse_categorical_accuracy: 0.4172


130/Unknown  65s 477ms/step - loss: 1.5917 - sparse_categorical_accuracy: 0.4179


131/Unknown  65s 477ms/step - loss: 1.5893 - sparse_categorical_accuracy: 0.4186


132/Unknown  66s 477ms/step - loss: 1.5869 - sparse_categorical_accuracy: 0.4193


133/Unknown  66s 477ms/step - loss: 1.5844 - sparse_categorical_accuracy: 0.4200


134/Unknown  66s 476ms/step - loss: 1.5820 - sparse_categorical_accuracy: 0.4207


135/Unknown  67s 476ms/step - loss: 1.5797 - sparse_categorical_accuracy: 0.4214


136/Unknown  67s 476ms/step - loss: 1.5773 - sparse_categorical_accuracy: 0.4221


137/Unknown  68s 475ms/step - loss: 1.5749 - sparse_categorical_accuracy: 0.4228


138/Unknown  68s 475ms/step - loss: 1.5726 - sparse_categorical_accuracy: 0.4235


139/Unknown  69s 475ms/step - loss: 1.5703 - sparse_categorical_accuracy: 0.4242


140/Unknown  69s 475ms/step - loss: 1.5680 - sparse_categorical_accuracy: 0.4249


141/Unknown  70s 474ms/step - loss: 1.5657 - sparse_categorical_accuracy: 0.4255


142/Unknown  70s 474ms/step - loss: 1.5634 - sparse_categorical_accuracy: 0.4262


143/Unknown  70s 474ms/step - loss: 1.5611 - sparse_categorical_accuracy: 0.4269


144/Unknown  71s 474ms/step - loss: 1.5589 - sparse_categorical_accuracy: 0.4276


145/Unknown  71s 474ms/step - loss: 1.5566 - sparse_categorical_accuracy: 0.4282


146/Unknown  72s 474ms/step - loss: 1.5544 - sparse_categorical_accuracy: 0.4289


147/Unknown  72s 474ms/step - loss: 1.5522 - sparse_categorical_accuracy: 0.4295


148/Unknown  73s 474ms/step - loss: 1.5500 - sparse_categorical_accuracy: 0.4302


149/Unknown  73s 473ms/step - loss: 1.5478 - sparse_categorical_accuracy: 0.4308


150/Unknown  74s 472ms/step - loss: 1.5456 - sparse_categorical_accuracy: 0.4315


151/Unknown  74s 472ms/step - loss: 1.5435 - sparse_categorical_accuracy: 0.4321


152/Unknown  74s 471ms/step - loss: 1.5413 - sparse_categorical_accuracy: 0.4328


153/Unknown  75s 470ms/step - loss: 1.5392 - sparse_categorical_accuracy: 0.4334


154/Unknown  75s 470ms/step - loss: 1.5370 - sparse_categorical_accuracy: 0.4340


155/Unknown  75s 469ms/step - loss: 1.5349 - sparse_categorical_accuracy: 0.4347


156/Unknown  76s 468ms/step - loss: 1.5328 - sparse_categorical_accuracy: 0.4353


157/Unknown  76s 468ms/step - loss: 1.5308 - sparse_categorical_accuracy: 0.4359


158/Unknown  76s 467ms/step - loss: 1.5287 - sparse_categorical_accuracy: 0.4365


159/Unknown  77s 467ms/step - loss: 1.5266 - sparse_categorical_accuracy: 0.4372


160/Unknown  77s 466ms/step - loss: 1.5246 - sparse_categorical_accuracy: 0.4378


161/Unknown  78s 466ms/step - loss: 1.5225 - sparse_categorical_accuracy: 0.4384


162/Unknown  78s 465ms/step - loss: 1.5205 - sparse_categorical_accuracy: 0.4390


163/Unknown  78s 464ms/step - loss: 1.5185 - sparse_categorical_accuracy: 0.4396


164/Unknown  79s 464ms/step - loss: 1.5165 - sparse_categorical_accuracy: 0.4402


165/Unknown  79s 463ms/step - loss: 1.5145 - sparse_categorical_accuracy: 0.4408


166/Unknown  79s 462ms/step - loss: 1.5126 - sparse_categorical_accuracy: 0.4414


167/Unknown  80s 462ms/step - loss: 1.5106 - sparse_categorical_accuracy: 0.4420


168/Unknown  80s 462ms/step - loss: 1.5087 - sparse_categorical_accuracy: 0.4425


169/Unknown  81s 462ms/step - loss: 1.5067 - sparse_categorical_accuracy: 0.4431


170/Unknown  81s 462ms/step - loss: 1.5048 - sparse_categorical_accuracy: 0.4437


171/Unknown  82s 461ms/step - loss: 1.5029 - sparse_categorical_accuracy: 0.4443


172/Unknown  82s 461ms/step - loss: 1.5010 - sparse_categorical_accuracy: 0.4449


173/Unknown  82s 461ms/step - loss: 1.4991 - sparse_categorical_accuracy: 0.4454


174/Unknown  83s 460ms/step - loss: 1.4972 - sparse_categorical_accuracy: 0.4460


175/Unknown  83s 460ms/step - loss: 1.4953 - sparse_categorical_accuracy: 0.4466


176/Unknown  83s 459ms/step - loss: 1.4935 - sparse_categorical_accuracy: 0.4471


177/Unknown  84s 458ms/step - loss: 1.4916 - sparse_categorical_accuracy: 0.4477


178/Unknown  84s 457ms/step - loss: 1.4898 - sparse_categorical_accuracy: 0.4482


179/Unknown  84s 457ms/step - loss: 1.4880 - sparse_categorical_accuracy: 0.4488


180/Unknown  85s 456ms/step - loss: 1.4861 - sparse_categorical_accuracy: 0.4493


181/Unknown  85s 455ms/step - loss: 1.4843 - sparse_categorical_accuracy: 0.4499


182/Unknown  85s 454ms/step - loss: 1.4825 - sparse_categorical_accuracy: 0.4504


183/Unknown  86s 454ms/step - loss: 1.4807 - sparse_categorical_accuracy: 0.4510


184/Unknown  86s 453ms/step - loss: 1.4790 - sparse_categorical_accuracy: 0.4515


185/Unknown  86s 452ms/step - loss: 1.4772 - sparse_categorical_accuracy: 0.4521


186/Unknown  87s 452ms/step - loss: 1.4754 - sparse_categorical_accuracy: 0.4526


187/Unknown  87s 451ms/step - loss: 1.4737 - sparse_categorical_accuracy: 0.4531


188/Unknown  87s 451ms/step - loss: 1.4719 - sparse_categorical_accuracy: 0.4537


189/Unknown  88s 450ms/step - loss: 1.4702 - sparse_categorical_accuracy: 0.4542


190/Unknown  88s 450ms/step - loss: 1.4685 - sparse_categorical_accuracy: 0.4547


191/Unknown  89s 450ms/step - loss: 1.4668 - sparse_categorical_accuracy: 0.4552


192/Unknown  89s 450ms/step - loss: 1.4651 - sparse_categorical_accuracy: 0.4557


193/Unknown  89s 450ms/step - loss: 1.4634 - sparse_categorical_accuracy: 0.4563


194/Unknown  90s 449ms/step - loss: 1.4617 - sparse_categorical_accuracy: 0.4568


195/Unknown  90s 449ms/step - loss: 1.4600 - sparse_categorical_accuracy: 0.4573


196/Unknown  91s 449ms/step - loss: 1.4583 - sparse_categorical_accuracy: 0.4578


197/Unknown  91s 449ms/step - loss: 1.4567 - sparse_categorical_accuracy: 0.4583


198/Unknown  92s 449ms/step - loss: 1.4550 - sparse_categorical_accuracy: 0.4588


199/Unknown  92s 449ms/step - loss: 1.4534 - sparse_categorical_accuracy: 0.4593


200/Unknown  92s 449ms/step - loss: 1.4517 - sparse_categorical_accuracy: 0.4598


201/Unknown  93s 448ms/step - loss: 1.4501 - sparse_categorical_accuracy: 0.4603


202/Unknown  93s 448ms/step - loss: 1.4485 - sparse_categorical_accuracy: 0.4608


203/Unknown  94s 447ms/step - loss: 1.4469 - sparse_categorical_accuracy: 0.4613


204/Unknown  94s 447ms/step - loss: 1.4453 - sparse_categorical_accuracy: 0.4618


205/Unknown  94s 447ms/step - loss: 1.4437 - sparse_categorical_accuracy: 0.4623


206/Unknown  95s 447ms/step - loss: 1.4421 - sparse_categorical_accuracy: 0.4628


207/Unknown  95s 446ms/step - loss: 1.4406 - sparse_categorical_accuracy: 0.4632


208/Unknown  95s 446ms/step - loss: 1.4390 - sparse_categorical_accuracy: 0.4637


209/Unknown  96s 445ms/step - loss: 1.4374 - sparse_categorical_accuracy: 0.4642


210/Unknown  96s 445ms/step - loss: 1.4359 - sparse_categorical_accuracy: 0.4647


211/Unknown  97s 445ms/step - loss: 1.4343 - sparse_categorical_accuracy: 0.4651


212/Unknown  97s 444ms/step - loss: 1.4328 - sparse_categorical_accuracy: 0.4656


213/Unknown  97s 444ms/step - loss: 1.4313 - sparse_categorical_accuracy: 0.4661


214/Unknown  98s 444ms/step - loss: 1.4297 - sparse_categorical_accuracy: 0.4666


215/Unknown  98s 444ms/step - loss: 1.4282 - sparse_categorical_accuracy: 0.4670


216/Unknown  99s 444ms/step - loss: 1.4267 - sparse_categorical_accuracy: 0.4675


217/Unknown  99s 445ms/step - loss: 1.4252 - sparse_categorical_accuracy: 0.4679


218/Unknown  100s 445ms/step - loss: 1.4237 - sparse_categorical_accuracy: 0.4684


219/Unknown  100s 445ms/step - loss: 1.4222 - sparse_categorical_accuracy: 0.4689


220/Unknown  101s 445ms/step - loss: 1.4207 - sparse_categorical_accuracy: 0.4693


221/Unknown  101s 444ms/step - loss: 1.4192 - sparse_categorical_accuracy: 0.4698


222/Unknown  101s 444ms/step - loss: 1.4178 - sparse_categorical_accuracy: 0.4702


223/Unknown  102s 444ms/step - loss: 1.4163 - sparse_categorical_accuracy: 0.4707


224/Unknown  102s 443ms/step - loss: 1.4149 - sparse_categorical_accuracy: 0.4711


225/Unknown  102s 443ms/step - loss: 1.4134 - sparse_categorical_accuracy: 0.4716


226/Unknown  103s 442ms/step - loss: 1.4120 - sparse_categorical_accuracy: 0.4720


227/Unknown  103s 442ms/step - loss: 1.4105 - sparse_categorical_accuracy: 0.4725


228/Unknown  103s 441ms/step - loss: 1.4091 - sparse_categorical_accuracy: 0.4729


229/Unknown  104s 441ms/step - loss: 1.4077 - sparse_categorical_accuracy: 0.4734


230/Unknown  104s 440ms/step - loss: 1.4063 - sparse_categorical_accuracy: 0.4738


231/Unknown  104s 440ms/step - loss: 1.4048 - sparse_categorical_accuracy: 0.4742


232/Unknown  105s 439ms/step - loss: 1.4034 - sparse_categorical_accuracy: 0.4747


233/Unknown  105s 439ms/step - loss: 1.4020 - sparse_categorical_accuracy: 0.4751


234/Unknown  105s 439ms/step - loss: 1.4007 - sparse_categorical_accuracy: 0.4755


235/Unknown  106s 438ms/step - loss: 1.3993 - sparse_categorical_accuracy: 0.4759


236/Unknown  106s 438ms/step - loss: 1.3979 - sparse_categorical_accuracy: 0.4764


237/Unknown  106s 437ms/step - loss: 1.3965 - sparse_categorical_accuracy: 0.4768


238/Unknown  107s 437ms/step - loss: 1.3952 - sparse_categorical_accuracy: 0.4772


239/Unknown  107s 437ms/step - loss: 1.3938 - sparse_categorical_accuracy: 0.4776


240/Unknown  108s 437ms/step - loss: 1.3925 - sparse_categorical_accuracy: 0.4780


241/Unknown  108s 437ms/step - loss: 1.3911 - sparse_categorical_accuracy: 0.4785


242/Unknown  109s 437ms/step - loss: 1.3898 - sparse_categorical_accuracy: 0.4789


243/Unknown  109s 437ms/step - loss: 1.3884 - sparse_categorical_accuracy: 0.4793


244/Unknown  109s 437ms/step - loss: 1.3871 - sparse_categorical_accuracy: 0.4797


245/Unknown  110s 437ms/step - loss: 1.3858 - sparse_categorical_accuracy: 0.4801


246/Unknown  110s 437ms/step - loss: 1.3845 - sparse_categorical_accuracy: 0.4805


247/Unknown  111s 437ms/step - loss: 1.3832 - sparse_categorical_accuracy: 0.4809


248/Unknown  111s 437ms/step - loss: 1.3819 - sparse_categorical_accuracy: 0.4813


249/Unknown  111s 436ms/step - loss: 1.3806 - sparse_categorical_accuracy: 0.4817


250/Unknown  112s 436ms/step - loss: 1.3793 - sparse_categorical_accuracy: 0.4821


251/Unknown  112s 435ms/step - loss: 1.3780 - sparse_categorical_accuracy: 0.4825


252/Unknown  112s 435ms/step - loss: 1.3767 - sparse_categorical_accuracy: 0.4829


253/Unknown  113s 435ms/step - loss: 1.3754 - sparse_categorical_accuracy: 0.4833


254/Unknown  113s 435ms/step - loss: 1.3742 - sparse_categorical_accuracy: 0.4837


255/Unknown  113s 434ms/step - loss: 1.3729 - sparse_categorical_accuracy: 0.4841


256/Unknown  114s 434ms/step - loss: 1.3716 - sparse_categorical_accuracy: 0.4845


257/Unknown  114s 434ms/step - loss: 1.3704 - sparse_categorical_accuracy: 0.4849


258/Unknown  115s 434ms/step - loss: 1.3691 - sparse_categorical_accuracy: 0.4853


259/Unknown  115s 433ms/step - loss: 1.3679 - sparse_categorical_accuracy: 0.4857


260/Unknown  115s 433ms/step - loss: 1.3666 - sparse_categorical_accuracy: 0.4861


261/Unknown  116s 433ms/step - loss: 1.3654 - sparse_categorical_accuracy: 0.4864


262/Unknown  116s 433ms/step - loss: 1.3642 - sparse_categorical_accuracy: 0.4868


263/Unknown  116s 433ms/step - loss: 1.3629 - sparse_categorical_accuracy: 0.4872


264/Unknown  117s 433ms/step - loss: 1.3617 - sparse_categorical_accuracy: 0.4876


265/Unknown  117s 432ms/step - loss: 1.3605 - sparse_categorical_accuracy: 0.4880


266/Unknown  118s 432ms/step - loss: 1.3593 - sparse_categorical_accuracy: 0.4883


267/Unknown  118s 432ms/step - loss: 1.3581 - sparse_categorical_accuracy: 0.4887


268/Unknown  118s 432ms/step - loss: 1.3569 - sparse_categorical_accuracy: 0.4891


269/Unknown  119s 432ms/step - loss: 1.3557 - sparse_categorical_accuracy: 0.4895


270/Unknown  119s 432ms/step - loss: 1.3545 - sparse_categorical_accuracy: 0.4898


271/Unknown  120s 432ms/step - loss: 1.3533 - sparse_categorical_accuracy: 0.4902


272/Unknown  120s 432ms/step - loss: 1.3521 - sparse_categorical_accuracy: 0.4906


273/Unknown  121s 432ms/step - loss: 1.3509 - sparse_categorical_accuracy: 0.4909


274/Unknown  121s 432ms/step - loss: 1.3497 - sparse_categorical_accuracy: 0.4913


275/Unknown  121s 432ms/step - loss: 1.3486 - sparse_categorical_accuracy: 0.4917


276/Unknown  122s 432ms/step - loss: 1.3474 - sparse_categorical_accuracy: 0.4920


277/Unknown  122s 432ms/step - loss: 1.3462 - sparse_categorical_accuracy: 0.4924


278/Unknown  123s 432ms/step - loss: 1.3451 - sparse_categorical_accuracy: 0.4928


279/Unknown  123s 431ms/step - loss: 1.3439 - sparse_categorical_accuracy: 0.4931


280/Unknown  123s 431ms/step - loss: 1.3428 - sparse_categorical_accuracy: 0.4935


281/Unknown  124s 431ms/step - loss: 1.3416 - sparse_categorical_accuracy: 0.4938


282/Unknown  124s 430ms/step - loss: 1.3405 - sparse_categorical_accuracy: 0.4942


283/Unknown  124s 430ms/step - loss: 1.3393 - sparse_categorical_accuracy: 0.4946


284/Unknown  125s 430ms/step - loss: 1.3382 - sparse_categorical_accuracy: 0.4949


285/Unknown  125s 430ms/step - loss: 1.3371 - sparse_categorical_accuracy: 0.4953


286/Unknown  126s 430ms/step - loss: 1.3360 - sparse_categorical_accuracy: 0.4956


287/Unknown  126s 430ms/step - loss: 1.3348 - sparse_categorical_accuracy: 0.4960


288/Unknown  126s 429ms/step - loss: 1.3337 - sparse_categorical_accuracy: 0.4963


289/Unknown  127s 429ms/step - loss: 1.3326 - sparse_categorical_accuracy: 0.4967


290/Unknown  127s 429ms/step - loss: 1.3315 - sparse_categorical_accuracy: 0.4970


291/Unknown  128s 429ms/step - loss: 1.3304 - sparse_categorical_accuracy: 0.4974


292/Unknown  128s 429ms/step - loss: 1.3293 - sparse_categorical_accuracy: 0.4977


293/Unknown  128s 429ms/step - loss: 1.3282 - sparse_categorical_accuracy: 0.4980


294/Unknown  129s 429ms/step - loss: 1.3271 - sparse_categorical_accuracy: 0.4984


295/Unknown  129s 429ms/step - loss: 1.3260 - sparse_categorical_accuracy: 0.4987


296/Unknown  130s 429ms/step - loss: 1.3250 - sparse_categorical_accuracy: 0.4991


297/Unknown  130s 429ms/step - loss: 1.3239 - sparse_categorical_accuracy: 0.4994


298/Unknown  131s 429ms/step - loss: 1.3228 - sparse_categorical_accuracy: 0.4997


299/Unknown  131s 429ms/step - loss: 1.3217 - sparse_categorical_accuracy: 0.5001


300/Unknown  132s 429ms/step - loss: 1.3207 - sparse_categorical_accuracy: 0.5004


301/Unknown  132s 429ms/step - loss: 1.3196 - sparse_categorical_accuracy: 0.5007


302/Unknown  132s 429ms/step - loss: 1.3186 - sparse_categorical_accuracy: 0.5011


303/Unknown  133s 429ms/step - loss: 1.3175 - sparse_categorical_accuracy: 0.5014


304/Unknown  133s 429ms/step - loss: 1.3165 - sparse_categorical_accuracy: 0.5017


305/Unknown  133s 429ms/step - loss: 1.3154 - sparse_categorical_accuracy: 0.5021


306/Unknown  134s 429ms/step - loss: 1.3144 - sparse_categorical_accuracy: 0.5024


307/Unknown  134s 428ms/step - loss: 1.3133 - sparse_categorical_accuracy: 0.5027


308/Unknown  135s 428ms/step - loss: 1.3123 - sparse_categorical_accuracy: 0.5030


309/Unknown  135s 428ms/step - loss: 1.3113 - sparse_categorical_accuracy: 0.5034


310/Unknown  135s 428ms/step - loss: 1.3103 - sparse_categorical_accuracy: 0.5037


311/Unknown  136s 428ms/step - loss: 1.3092 - sparse_categorical_accuracy: 0.5040


312/Unknown  136s 428ms/step - loss: 1.3082 - sparse_categorical_accuracy: 0.5043


313/Unknown  136s 427ms/step - loss: 1.3072 - sparse_categorical_accuracy: 0.5047


314/Unknown  137s 427ms/step - loss: 1.3062 - sparse_categorical_accuracy: 0.5050


315/Unknown  137s 427ms/step - loss: 1.3052 - sparse_categorical_accuracy: 0.5053


316/Unknown  138s 427ms/step - loss: 1.3042 - sparse_categorical_accuracy: 0.5056


317/Unknown  138s 427ms/step - loss: 1.3032 - sparse_categorical_accuracy: 0.5059


318/Unknown  138s 427ms/step - loss: 1.3022 - sparse_categorical_accuracy: 0.5062


319/Unknown  139s 427ms/step - loss: 1.3012 - sparse_categorical_accuracy: 0.5066


320/Unknown  139s 426ms/step - loss: 1.3002 - sparse_categorical_accuracy: 0.5069


321/Unknown  140s 427ms/step - loss: 1.2992 - sparse_categorical_accuracy: 0.5072


322/Unknown  140s 427ms/step - loss: 1.2982 - sparse_categorical_accuracy: 0.5075


323/Unknown  141s 427ms/step - loss: 1.2973 - sparse_categorical_accuracy: 0.5078


324/Unknown  141s 427ms/step - loss: 1.2963 - sparse_categorical_accuracy: 0.5081


325/Unknown  141s 427ms/step - loss: 1.2953 - sparse_categorical_accuracy: 0.5084


326/Unknown  142s 427ms/step - loss: 1.2943 - sparse_categorical_accuracy: 0.5087


327/Unknown  142s 427ms/step - loss: 1.2934 - sparse_categorical_accuracy: 0.5090


328/Unknown  143s 427ms/step - loss: 1.2924 - sparse_categorical_accuracy: 0.5093


329/Unknown  143s 426ms/step - loss: 1.2915 - sparse_categorical_accuracy: 0.5096


330/Unknown  143s 426ms/step - loss: 1.2905 - sparse_categorical_accuracy: 0.5099


331/Unknown  144s 426ms/step - loss: 1.2895 - sparse_categorical_accuracy: 0.5103


332/Unknown  144s 426ms/step - loss: 1.2886 - sparse_categorical_accuracy: 0.5106


333/Unknown  145s 426ms/step - loss: 1.2876 - sparse_categorical_accuracy: 0.5109


334/Unknown  145s 426ms/step - loss: 1.2867 - sparse_categorical_accuracy: 0.5112


335/Unknown  145s 426ms/step - loss: 1.2858 - sparse_categorical_accuracy: 0.5115


336/Unknown  146s 426ms/step - loss: 1.2848 - sparse_categorical_accuracy: 0.5118


337/Unknown  146s 426ms/step - loss: 1.2839 - sparse_categorical_accuracy: 0.5121


338/Unknown  146s 425ms/step - loss: 1.2830 - sparse_categorical_accuracy: 0.5124


339/Unknown  147s 425ms/step - loss: 1.2820 - sparse_categorical_accuracy: 0.5126


340/Unknown  147s 425ms/step - loss: 1.2811 - sparse_categorical_accuracy: 0.5129


341/Unknown  148s 425ms/step - loss: 1.2802 - sparse_categorical_accuracy: 0.5132


342/Unknown  148s 425ms/step - loss: 1.2793 - sparse_categorical_accuracy: 0.5135


343/Unknown  149s 425ms/step - loss: 1.2784 - sparse_categorical_accuracy: 0.5138


344/Unknown  149s 425ms/step - loss: 1.2775 - sparse_categorical_accuracy: 0.5141


345/Unknown  149s 425ms/step - loss: 1.2765 - sparse_categorical_accuracy: 0.5144


346/Unknown  150s 426ms/step - loss: 1.2756 - sparse_categorical_accuracy: 0.5147


347/Unknown  150s 425ms/step - loss: 1.2747 - sparse_categorical_accuracy: 0.5150


348/Unknown  151s 425ms/step - loss: 1.2738 - sparse_categorical_accuracy: 0.5153


349/Unknown  151s 425ms/step - loss: 1.2729 - sparse_categorical_accuracy: 0.5156


350/Unknown  151s 425ms/step - loss: 1.2721 - sparse_categorical_accuracy: 0.5158


351/Unknown  152s 425ms/step - loss: 1.2712 - sparse_categorical_accuracy: 0.5161


352/Unknown  152s 424ms/step - loss: 1.2703 - sparse_categorical_accuracy: 0.5164


353/Unknown  152s 424ms/step - loss: 1.2694 - sparse_categorical_accuracy: 0.5167


354/Unknown  153s 424ms/step - loss: 1.2685 - sparse_categorical_accuracy: 0.5170


355/Unknown  153s 423ms/step - loss: 1.2676 - sparse_categorical_accuracy: 0.5172


356/Unknown  153s 423ms/step - loss: 1.2668 - sparse_categorical_accuracy: 0.5175


357/Unknown  154s 423ms/step - loss: 1.2659 - sparse_categorical_accuracy: 0.5178


358/Unknown  154s 423ms/step - loss: 1.2650 - sparse_categorical_accuracy: 0.5181


359/Unknown  154s 422ms/step - loss: 1.2642 - sparse_categorical_accuracy: 0.5184


360/Unknown  155s 422ms/step - loss: 1.2633 - sparse_categorical_accuracy: 0.5186


361/Unknown  155s 422ms/step - loss: 1.2624 - sparse_categorical_accuracy: 0.5189


362/Unknown  155s 422ms/step - loss: 1.2616 - sparse_categorical_accuracy: 0.5192


363/Unknown  156s 422ms/step - loss: 1.2607 - sparse_categorical_accuracy: 0.5195


364/Unknown  156s 421ms/step - loss: 1.2599 - sparse_categorical_accuracy: 0.5197


365/Unknown  156s 421ms/step - loss: 1.2590 - sparse_categorical_accuracy: 0.5200


366/Unknown  157s 421ms/step - loss: 1.2582 - sparse_categorical_accuracy: 0.5203


367/Unknown  157s 421ms/step - loss: 1.2573 - sparse_categorical_accuracy: 0.5206


368/Unknown  158s 421ms/step - loss: 1.2565 - sparse_categorical_accuracy: 0.5208


369/Unknown  158s 421ms/step - loss: 1.2557 - sparse_categorical_accuracy: 0.5211


370/Unknown  159s 421ms/step - loss: 1.2548 - sparse_categorical_accuracy: 0.5214


371/Unknown  159s 421ms/step - loss: 1.2540 - sparse_categorical_accuracy: 0.5216


372/Unknown  159s 421ms/step - loss: 1.2532 - sparse_categorical_accuracy: 0.5219


373/Unknown  160s 420ms/step - loss: 1.2523 - sparse_categorical_accuracy: 0.5222


374/Unknown  160s 420ms/step - loss: 1.2515 - sparse_categorical_accuracy: 0.5224


375/Unknown  160s 420ms/step - loss: 1.2507 - sparse_categorical_accuracy: 0.5227


376/Unknown  161s 420ms/step - loss: 1.2499 - sparse_categorical_accuracy: 0.5230


377/Unknown  161s 420ms/step - loss: 1.2491 - sparse_categorical_accuracy: 0.5232


378/Unknown  161s 420ms/step - loss: 1.2482 - sparse_categorical_accuracy: 0.5235


379/Unknown  162s 420ms/step - loss: 1.2474 - sparse_categorical_accuracy: 0.5237


380/Unknown  162s 420ms/step - loss: 1.2466 - sparse_categorical_accuracy: 0.5240


381/Unknown  163s 419ms/step - loss: 1.2458 - sparse_categorical_accuracy: 0.5243


382/Unknown  163s 419ms/step - loss: 1.2450 - sparse_categorical_accuracy: 0.5245


383/Unknown  163s 419ms/step - loss: 1.2442 - sparse_categorical_accuracy: 0.5248


384/Unknown  164s 419ms/step - loss: 1.2434 - sparse_categorical_accuracy: 0.5250


385/Unknown  164s 419ms/step - loss: 1.2426 - sparse_categorical_accuracy: 0.5253


386/Unknown  165s 419ms/step - loss: 1.2418 - sparse_categorical_accuracy: 0.5256


387/Unknown  165s 419ms/step - loss: 1.2410 - sparse_categorical_accuracy: 0.5258


388/Unknown  165s 419ms/step - loss: 1.2402 - sparse_categorical_accuracy: 0.5261


389/Unknown  166s 419ms/step - loss: 1.2395 - sparse_categorical_accuracy: 0.5263


390/Unknown  166s 419ms/step - loss: 1.2387 - sparse_categorical_accuracy: 0.5266


391/Unknown  167s 419ms/step - loss: 1.2379 - sparse_categorical_accuracy: 0.5268


392/Unknown  167s 419ms/step - loss: 1.2371 - sparse_categorical_accuracy: 0.5271


393/Unknown  167s 419ms/step - loss: 1.2363 - sparse_categorical_accuracy: 0.5273


394/Unknown  168s 419ms/step - loss: 1.2356 - sparse_categorical_accuracy: 0.5276


395/Unknown  168s 419ms/step - loss: 1.2348 - sparse_categorical_accuracy: 0.5278


396/Unknown  168s 419ms/step - loss: 1.2340 - sparse_categorical_accuracy: 0.5281


397/Unknown  169s 418ms/step - loss: 1.2333 - sparse_categorical_accuracy: 0.5283


398/Unknown  169s 418ms/step - loss: 1.2325 - sparse_categorical_accuracy: 0.5286


399/Unknown  170s 418ms/step - loss: 1.2317 - sparse_categorical_accuracy: 0.5288


400/Unknown  170s 418ms/step - loss: 1.2310 - sparse_categorical_accuracy: 0.5290


401/Unknown  170s 418ms/step - loss: 1.2302 - sparse_categorical_accuracy: 0.5293


402/Unknown  171s 418ms/step - loss: 1.2295 - sparse_categorical_accuracy: 0.5295


403/Unknown  171s 418ms/step - loss: 1.2287 - sparse_categorical_accuracy: 0.5298


404/Unknown  171s 418ms/step - loss: 1.2280 - sparse_categorical_accuracy: 0.5300


405/Unknown  172s 418ms/step - loss: 1.2272 - sparse_categorical_accuracy: 0.5303


406/Unknown  172s 418ms/step - loss: 1.2265 - sparse_categorical_accuracy: 0.5305


407/Unknown  173s 418ms/step - loss: 1.2257 - sparse_categorical_accuracy: 0.5307


408/Unknown  173s 418ms/step - loss: 1.2250 - sparse_categorical_accuracy: 0.5310


409/Unknown  174s 418ms/step - loss: 1.2243 - sparse_categorical_accuracy: 0.5312


410/Unknown  174s 418ms/step - loss: 1.2235 - sparse_categorical_accuracy: 0.5314


411/Unknown  175s 418ms/step - loss: 1.2228 - sparse_categorical_accuracy: 0.5317


412/Unknown  175s 419ms/step - loss: 1.2221 - sparse_categorical_accuracy: 0.5319


413/Unknown  176s 419ms/step - loss: 1.2213 - sparse_categorical_accuracy: 0.5322


414/Unknown  176s 419ms/step - loss: 1.2206 - sparse_categorical_accuracy: 0.5324


415/Unknown  176s 419ms/step - loss: 1.2199 - sparse_categorical_accuracy: 0.5326


416/Unknown  177s 419ms/step - loss: 1.2192 - sparse_categorical_accuracy: 0.5329


417/Unknown  177s 418ms/step - loss: 1.2185 - sparse_categorical_accuracy: 0.5331


418/Unknown  177s 418ms/step - loss: 1.2177 - sparse_categorical_accuracy: 0.5333


419/Unknown  178s 418ms/step - loss: 1.2170 - sparse_categorical_accuracy: 0.5336


420/Unknown  178s 418ms/step - loss: 1.2163 - sparse_categorical_accuracy: 0.5338


421/Unknown  179s 418ms/step - loss: 1.2156 - sparse_categorical_accuracy: 0.5340


422/Unknown  179s 418ms/step - loss: 1.2149 - sparse_categorical_accuracy: 0.5342


423/Unknown  179s 418ms/step - loss: 1.2142 - sparse_categorical_accuracy: 0.5345


424/Unknown  180s 417ms/step - loss: 1.2135 - sparse_categorical_accuracy: 0.5347


425/Unknown  180s 417ms/step - loss: 1.2128 - sparse_categorical_accuracy: 0.5349


426/Unknown  180s 417ms/step - loss: 1.2121 - sparse_categorical_accuracy: 0.5351


427/Unknown  181s 417ms/step - loss: 1.2114 - sparse_categorical_accuracy: 0.5354


428/Unknown  181s 417ms/step - loss: 1.2107 - sparse_categorical_accuracy: 0.5356


429/Unknown  182s 417ms/step - loss: 1.2100 - sparse_categorical_accuracy: 0.5358


430/Unknown  182s 418ms/step - loss: 1.2093 - sparse_categorical_accuracy: 0.5360


431/Unknown  183s 418ms/step - loss: 1.2086 - sparse_categorical_accuracy: 0.5363


432/Unknown  183s 418ms/step - loss: 1.2079 - sparse_categorical_accuracy: 0.5365


433/Unknown  184s 418ms/step - loss: 1.2072 - sparse_categorical_accuracy: 0.5367


434/Unknown  184s 418ms/step - loss: 1.2065 - sparse_categorical_accuracy: 0.5369


435/Unknown  185s 418ms/step - loss: 1.2059 - sparse_categorical_accuracy: 0.5372


436/Unknown  185s 418ms/step - loss: 1.2052 - sparse_categorical_accuracy: 0.5374


437/Unknown  185s 418ms/step - loss: 1.2045 - sparse_categorical_accuracy: 0.5376


438/Unknown  186s 418ms/step - loss: 1.2038 - sparse_categorical_accuracy: 0.5378


439/Unknown  186s 418ms/step - loss: 1.2032 - sparse_categorical_accuracy: 0.5380


440/Unknown  187s 418ms/step - loss: 1.2025 - sparse_categorical_accuracy: 0.5383


441/Unknown  187s 418ms/step - loss: 1.2018 - sparse_categorical_accuracy: 0.5385


442/Unknown  187s 418ms/step - loss: 1.2011 - sparse_categorical_accuracy: 0.5387


443/Unknown  188s 418ms/step - loss: 1.2005 - sparse_categorical_accuracy: 0.5389


444/Unknown  188s 417ms/step - loss: 1.1998 - sparse_categorical_accuracy: 0.5391


445/Unknown  188s 417ms/step - loss: 1.1992 - sparse_categorical_accuracy: 0.5393


446/Unknown  189s 417ms/step - loss: 1.1985 - sparse_categorical_accuracy: 0.5396


447/Unknown  189s 417ms/step - loss: 1.1978 - sparse_categorical_accuracy: 0.5398


448/Unknown  190s 417ms/step - loss: 1.1972 - sparse_categorical_accuracy: 0.5400


449/Unknown  190s 417ms/step - loss: 1.1965 - sparse_categorical_accuracy: 0.5402


450/Unknown  190s 417ms/step - loss: 1.1959 - sparse_categorical_accuracy: 0.5404


451/Unknown  191s 417ms/step - loss: 1.1952 - sparse_categorical_accuracy: 0.5406


452/Unknown  191s 417ms/step - loss: 1.1946 - sparse_categorical_accuracy: 0.5408


453/Unknown  191s 417ms/step - loss: 1.1939 - sparse_categorical_accuracy: 0.5410


454/Unknown  192s 417ms/step - loss: 1.1933 - sparse_categorical_accuracy: 0.5413


455/Unknown  192s 417ms/step - loss: 1.1926 - sparse_categorical_accuracy: 0.5415


456/Unknown  193s 417ms/step - loss: 1.1920 - sparse_categorical_accuracy: 0.5417


457/Unknown  193s 417ms/step - loss: 1.1913 - sparse_categorical_accuracy: 0.5419


458/Unknown  193s 417ms/step - loss: 1.1907 - sparse_categorical_accuracy: 0.5421


459/Unknown  194s 417ms/step - loss: 1.1900 - sparse_categorical_accuracy: 0.5423


460/Unknown  194s 417ms/step - loss: 1.1894 - sparse_categorical_accuracy: 0.5425


461/Unknown  195s 417ms/step - loss: 1.1888 - sparse_categorical_accuracy: 0.5427


462/Unknown  195s 417ms/step - loss: 1.1881 - sparse_categorical_accuracy: 0.5429


463/Unknown  196s 417ms/step - loss: 1.1875 - sparse_categorical_accuracy: 0.5431


464/Unknown  196s 417ms/step - loss: 1.1869 - sparse_categorical_accuracy: 0.5433


465/Unknown  197s 417ms/step - loss: 1.1862 - sparse_categorical_accuracy: 0.5435


466/Unknown  197s 417ms/step - loss: 1.1856 - sparse_categorical_accuracy: 0.5437


467/Unknown  198s 417ms/step - loss: 1.1850 - sparse_categorical_accuracy: 0.5439


468/Unknown  198s 417ms/step - loss: 1.1844 - sparse_categorical_accuracy: 0.5441


469/Unknown  198s 417ms/step - loss: 1.1837 - sparse_categorical_accuracy: 0.5443


470/Unknown  199s 417ms/step - loss: 1.1831 - sparse_categorical_accuracy: 0.5446


471/Unknown  199s 417ms/step - loss: 1.1825 - sparse_categorical_accuracy: 0.5448


472/Unknown  199s 417ms/step - loss: 1.1819 - sparse_categorical_accuracy: 0.5450


473/Unknown  200s 417ms/step - loss: 1.1813 - sparse_categorical_accuracy: 0.5452


474/Unknown  200s 417ms/step - loss: 1.1807 - sparse_categorical_accuracy: 0.5454


475/Unknown  201s 417ms/step - loss: 1.1800 - sparse_categorical_accuracy: 0.5456


476/Unknown  201s 416ms/step - loss: 1.1794 - sparse_categorical_accuracy: 0.5458


477/Unknown  201s 417ms/step - loss: 1.1788 - sparse_categorical_accuracy: 0.5460


478/Unknown  202s 416ms/step - loss: 1.1782 - sparse_categorical_accuracy: 0.5461


479/Unknown  202s 416ms/step - loss: 1.1776 - sparse_categorical_accuracy: 0.5463


480/Unknown  203s 416ms/step - loss: 1.1770 - sparse_categorical_accuracy: 0.5465


481/Unknown  203s 416ms/step - loss: 1.1764 - sparse_categorical_accuracy: 0.5467


482/Unknown  203s 416ms/step - loss: 1.1758 - sparse_categorical_accuracy: 0.5469


483/Unknown  204s 416ms/step - loss: 1.1752 - sparse_categorical_accuracy: 0.5471


484/Unknown  204s 416ms/step - loss: 1.1746 - sparse_categorical_accuracy: 0.5473


485/Unknown  205s 416ms/step - loss: 1.1740 - sparse_categorical_accuracy: 0.5475


486/Unknown  205s 416ms/step - loss: 1.1734 - sparse_categorical_accuracy: 0.5477


487/Unknown  205s 416ms/step - loss: 1.1728 - sparse_categorical_accuracy: 0.5479


488/Unknown  206s 416ms/step - loss: 1.1722 - sparse_categorical_accuracy: 0.5481


489/Unknown  206s 416ms/step - loss: 1.1716 - sparse_categorical_accuracy: 0.5483


490/Unknown  207s 416ms/step - loss: 1.1711 - sparse_categorical_accuracy: 0.5485


491/Unknown  207s 416ms/step - loss: 1.1705 - sparse_categorical_accuracy: 0.5487


492/Unknown  207s 416ms/step - loss: 1.1699 - sparse_categorical_accuracy: 0.5489


493/Unknown  208s 416ms/step - loss: 1.1693 - sparse_categorical_accuracy: 0.5491


494/Unknown  208s 416ms/step - loss: 1.1687 - sparse_categorical_accuracy: 0.5493


495/Unknown  208s 416ms/step - loss: 1.1681 - sparse_categorical_accuracy: 0.5494


496/Unknown  209s 416ms/step - loss: 1.1676 - sparse_categorical_accuracy: 0.5496


497/Unknown  209s 416ms/step - loss: 1.1670 - sparse_categorical_accuracy: 0.5498


498/Unknown  210s 416ms/step - loss: 1.1664 - sparse_categorical_accuracy: 0.5500


499/Unknown  210s 415ms/step - loss: 1.1658 - sparse_categorical_accuracy: 0.5502


500/Unknown  210s 415ms/step - loss: 1.1652 - sparse_categorical_accuracy: 0.5504


501/Unknown  211s 415ms/step - loss: 1.1647 - sparse_categorical_accuracy: 0.5506


502/Unknown  211s 415ms/step - loss: 1.1641 - sparse_categorical_accuracy: 0.5508


503/Unknown  212s 415ms/step - loss: 1.1635 - sparse_categorical_accuracy: 0.5509


504/Unknown  212s 415ms/step - loss: 1.1630 - sparse_categorical_accuracy: 0.5511


505/Unknown  212s 415ms/step - loss: 1.1624 - sparse_categorical_accuracy: 0.5513


506/Unknown  213s 415ms/step - loss: 1.1618 - sparse_categorical_accuracy: 0.5515


507/Unknown  213s 416ms/step - loss: 1.1613 - sparse_categorical_accuracy: 0.5517


508/Unknown  214s 416ms/step - loss: 1.1607 - sparse_categorical_accuracy: 0.5519


509/Unknown  214s 416ms/step - loss: 1.1601 - sparse_categorical_accuracy: 0.5521


510/Unknown  215s 416ms/step - loss: 1.1596 - sparse_categorical_accuracy: 0.5522


511/Unknown  215s 416ms/step - loss: 1.1590 - sparse_categorical_accuracy: 0.5524


512/Unknown  216s 416ms/step - loss: 1.1585 - sparse_categorical_accuracy: 0.5526


513/Unknown  216s 415ms/step - loss: 1.1579 - sparse_categorical_accuracy: 0.5528


514/Unknown  216s 415ms/step - loss: 1.1574 - sparse_categorical_accuracy: 0.5530


515/Unknown  217s 415ms/step - loss: 1.1568 - sparse_categorical_accuracy: 0.5531


516/Unknown  217s 415ms/step - loss: 1.1562 - sparse_categorical_accuracy: 0.5533


517/Unknown  217s 415ms/step - loss: 1.1557 - sparse_categorical_accuracy: 0.5535


518/Unknown  218s 415ms/step - loss: 1.1551 - sparse_categorical_accuracy: 0.5537


519/Unknown  218s 415ms/step - loss: 1.1546 - sparse_categorical_accuracy: 0.5539


520/Unknown  218s 415ms/step - loss: 1.1541 - sparse_categorical_accuracy: 0.5540


521/Unknown  219s 415ms/step - loss: 1.1535 - sparse_categorical_accuracy: 0.5542


522/Unknown  219s 415ms/step - loss: 1.1530 - sparse_categorical_accuracy: 0.5544


523/Unknown  219s 414ms/step - loss: 1.1524 - sparse_categorical_accuracy: 0.5546


524/Unknown  220s 415ms/step - loss: 1.1519 - sparse_categorical_accuracy: 0.5548


525/Unknown  220s 415ms/step - loss: 1.1513 - sparse_categorical_accuracy: 0.5549


526/Unknown  221s 415ms/step - loss: 1.1508 - sparse_categorical_accuracy: 0.5551


527/Unknown  221s 415ms/step - loss: 1.1503 - sparse_categorical_accuracy: 0.5553


528/Unknown  222s 415ms/step - loss: 1.1497 - sparse_categorical_accuracy: 0.5555


529/Unknown  222s 415ms/step - loss: 1.1492 - sparse_categorical_accuracy: 0.5556


530/Unknown  223s 415ms/step - loss: 1.1487 - sparse_categorical_accuracy: 0.5558


531/Unknown  223s 415ms/step - loss: 1.1481 - sparse_categorical_accuracy: 0.5560


532/Unknown  223s 415ms/step - loss: 1.1476 - sparse_categorical_accuracy: 0.5562


533/Unknown  224s 415ms/step - loss: 1.1471 - sparse_categorical_accuracy: 0.5563


534/Unknown  224s 415ms/step - loss: 1.1465 - sparse_categorical_accuracy: 0.5565


535/Unknown  225s 415ms/step - loss: 1.1460 - sparse_categorical_accuracy: 0.5567


536/Unknown  225s 415ms/step - loss: 1.1455 - sparse_categorical_accuracy: 0.5569


537/Unknown  226s 415ms/step - loss: 1.1450 - sparse_categorical_accuracy: 0.5570


538/Unknown  226s 415ms/step - loss: 1.1444 - sparse_categorical_accuracy: 0.5572


539/Unknown  227s 415ms/step - loss: 1.1439 - sparse_categorical_accuracy: 0.5574


540/Unknown  227s 415ms/step - loss: 1.1434 - sparse_categorical_accuracy: 0.5575


541/Unknown  227s 415ms/step - loss: 1.1429 - sparse_categorical_accuracy: 0.5577


542/Unknown  228s 415ms/step - loss: 1.1424 - sparse_categorical_accuracy: 0.5579


543/Unknown  228s 415ms/step - loss: 1.1418 - sparse_categorical_accuracy: 0.5581


544/Unknown  228s 415ms/step - loss: 1.1413 - sparse_categorical_accuracy: 0.5582


545/Unknown  229s 415ms/step - loss: 1.1408 - sparse_categorical_accuracy: 0.5584


546/Unknown  229s 415ms/step - loss: 1.1403 - sparse_categorical_accuracy: 0.5586


547/Unknown  230s 415ms/step - loss: 1.1398 - sparse_categorical_accuracy: 0.5587


548/Unknown  230s 415ms/step - loss: 1.1393 - sparse_categorical_accuracy: 0.5589


549/Unknown  230s 415ms/step - loss: 1.1388 - sparse_categorical_accuracy: 0.5591


550/Unknown  231s 415ms/step - loss: 1.1383 - sparse_categorical_accuracy: 0.5592


551/Unknown  231s 415ms/step - loss: 1.1378 - sparse_categorical_accuracy: 0.5594


552/Unknown  232s 415ms/step - loss: 1.1373 - sparse_categorical_accuracy: 0.5596


553/Unknown  232s 414ms/step - loss: 1.1368 - sparse_categorical_accuracy: 0.5597


554/Unknown  232s 414ms/step - loss: 1.1362 - sparse_categorical_accuracy: 0.5599


555/Unknown  233s 414ms/step - loss: 1.1357 - sparse_categorical_accuracy: 0.5601


556/Unknown  233s 414ms/step - loss: 1.1352 - sparse_categorical_accuracy: 0.5602


557/Unknown  233s 414ms/step - loss: 1.1347 - sparse_categorical_accuracy: 0.5604


558/Unknown  234s 414ms/step - loss: 1.1342 - sparse_categorical_accuracy: 0.5605


559/Unknown  234s 415ms/step - loss: 1.1338 - sparse_categorical_accuracy: 0.5607


560/Unknown  235s 415ms/step - loss: 1.1333 - sparse_categorical_accuracy: 0.5609


561/Unknown  235s 415ms/step - loss: 1.1328 - sparse_categorical_accuracy: 0.5610


562/Unknown  236s 415ms/step - loss: 1.1323 - sparse_categorical_accuracy: 0.5612


563/Unknown  236s 415ms/step - loss: 1.1318 - sparse_categorical_accuracy: 0.5614


564/Unknown  237s 415ms/step - loss: 1.1313 - sparse_categorical_accuracy: 0.5615


565/Unknown  237s 415ms/step - loss: 1.1308 - sparse_categorical_accuracy: 0.5617


566/Unknown  238s 415ms/step - loss: 1.1303 - sparse_categorical_accuracy: 0.5618


567/Unknown  238s 415ms/step - loss: 1.1298 - sparse_categorical_accuracy: 0.5620


568/Unknown  238s 415ms/step - loss: 1.1293 - sparse_categorical_accuracy: 0.5622


569/Unknown  239s 415ms/step - loss: 1.1288 - sparse_categorical_accuracy: 0.5623


570/Unknown  239s 415ms/step - loss: 1.1284 - sparse_categorical_accuracy: 0.5625


571/Unknown  240s 415ms/step - loss: 1.1279 - sparse_categorical_accuracy: 0.5626


572/Unknown  240s 415ms/step - loss: 1.1274 - sparse_categorical_accuracy: 0.5628


573/Unknown  240s 415ms/step - loss: 1.1269 - sparse_categorical_accuracy: 0.5630


574/Unknown  241s 415ms/step - loss: 1.1264 - sparse_categorical_accuracy: 0.5631


575/Unknown  241s 415ms/step - loss: 1.1260 - sparse_categorical_accuracy: 0.5633


576/Unknown  241s 414ms/step - loss: 1.1255 - sparse_categorical_accuracy: 0.5634


577/Unknown  242s 414ms/step - loss: 1.1250 - sparse_categorical_accuracy: 0.5636


578/Unknown  242s 414ms/step - loss: 1.1245 - sparse_categorical_accuracy: 0.5638


579/Unknown  242s 414ms/step - loss: 1.1240 - sparse_categorical_accuracy: 0.5639


580/Unknown  243s 414ms/step - loss: 1.1236 - sparse_categorical_accuracy: 0.5641


581/Unknown  243s 414ms/step - loss: 1.1231 - sparse_categorical_accuracy: 0.5642


582/Unknown  243s 413ms/step - loss: 1.1226 - sparse_categorical_accuracy: 0.5644


583/Unknown  244s 413ms/step - loss: 1.1222 - sparse_categorical_accuracy: 0.5645


584/Unknown  244s 413ms/step - loss: 1.1217 - sparse_categorical_accuracy: 0.5647


585/Unknown  244s 413ms/step - loss: 1.1212 - sparse_categorical_accuracy: 0.5648


586/Unknown  245s 413ms/step - loss: 1.1207 - sparse_categorical_accuracy: 0.5650


587/Unknown  245s 413ms/step - loss: 1.1203 - sparse_categorical_accuracy: 0.5651


588/Unknown  246s 413ms/step - loss: 1.1198 - sparse_categorical_accuracy: 0.5653


589/Unknown  246s 413ms/step - loss: 1.1194 - sparse_categorical_accuracy: 0.5655


590/Unknown  246s 413ms/step - loss: 1.1189 - sparse_categorical_accuracy: 0.5656


591/Unknown  247s 413ms/step - loss: 1.1184 - sparse_categorical_accuracy: 0.5658


592/Unknown  247s 413ms/step - loss: 1.1180 - sparse_categorical_accuracy: 0.5659


593/Unknown  248s 413ms/step - loss: 1.1175 - sparse_categorical_accuracy: 0.5661


594/Unknown  248s 413ms/step - loss: 1.1171 - sparse_categorical_accuracy: 0.5662


595/Unknown  248s 413ms/step - loss: 1.1166 - sparse_categorical_accuracy: 0.5664


596/Unknown  249s 413ms/step - loss: 1.1161 - sparse_categorical_accuracy: 0.5665


597/Unknown  249s 413ms/step - loss: 1.1157 - sparse_categorical_accuracy: 0.5667


598/Unknown  249s 413ms/step - loss: 1.1152 - sparse_categorical_accuracy: 0.5668


599/Unknown  250s 413ms/step - loss: 1.1148 - sparse_categorical_accuracy: 0.5670


600/Unknown  250s 413ms/step - loss: 1.1143 - sparse_categorical_accuracy: 0.5671


601/Unknown  251s 412ms/step - loss: 1.1139 - sparse_categorical_accuracy: 0.5673


602/Unknown  251s 412ms/step - loss: 1.1134 - sparse_categorical_accuracy: 0.5674


603/Unknown  251s 412ms/step - loss: 1.1130 - sparse_categorical_accuracy: 0.5676


604/Unknown  252s 412ms/step - loss: 1.1125 - sparse_categorical_accuracy: 0.5677


605/Unknown  252s 412ms/step - loss: 1.1121 - sparse_categorical_accuracy: 0.5679


606/Unknown  252s 412ms/step - loss: 1.1116 - sparse_categorical_accuracy: 0.5680


607/Unknown  253s 412ms/step - loss: 1.1112 - sparse_categorical_accuracy: 0.5682


608/Unknown  253s 412ms/step - loss: 1.1107 - sparse_categorical_accuracy: 0.5683


609/Unknown  254s 412ms/step - loss: 1.1103 - sparse_categorical_accuracy: 0.5685


610/Unknown  254s 412ms/step - loss: 1.1098 - sparse_categorical_accuracy: 0.5686


611/Unknown  255s 412ms/step - loss: 1.1094 - sparse_categorical_accuracy: 0.5687


612/Unknown  255s 412ms/step - loss: 1.1090 - sparse_categorical_accuracy: 0.5689


613/Unknown  255s 412ms/step - loss: 1.1085 - sparse_categorical_accuracy: 0.5690


614/Unknown  256s 412ms/step - loss: 1.1081 - sparse_categorical_accuracy: 0.5692


615/Unknown  256s 412ms/step - loss: 1.1076 - sparse_categorical_accuracy: 0.5693


616/Unknown  257s 413ms/step - loss: 1.1072 - sparse_categorical_accuracy: 0.5695


617/Unknown  257s 413ms/step - loss: 1.1068 - sparse_categorical_accuracy: 0.5696


618/Unknown  258s 413ms/step - loss: 1.1063 - sparse_categorical_accuracy: 0.5698


619/Unknown  258s 413ms/step - loss: 1.1059 - sparse_categorical_accuracy: 0.5699


620/Unknown  259s 413ms/step - loss: 1.1055 - sparse_categorical_accuracy: 0.5700


621/Unknown  259s 413ms/step - loss: 1.1050 - sparse_categorical_accuracy: 0.5702


622/Unknown  260s 413ms/step - loss: 1.1046 - sparse_categorical_accuracy: 0.5703


623/Unknown  260s 413ms/step - loss: 1.1042 - sparse_categorical_accuracy: 0.5705


624/Unknown  261s 413ms/step - loss: 1.1037 - sparse_categorical_accuracy: 0.5706


625/Unknown  261s 413ms/step - loss: 1.1033 - sparse_categorical_accuracy: 0.5708


626/Unknown  261s 413ms/step - loss: 1.1029 - sparse_categorical_accuracy: 0.5709


627/Unknown  262s 413ms/step - loss: 1.1025 - sparse_categorical_accuracy: 0.5710


628/Unknown  262s 413ms/step - loss: 1.1020 - sparse_categorical_accuracy: 0.5712


629/Unknown  263s 413ms/step - loss: 1.1016 - sparse_categorical_accuracy: 0.5713


630/Unknown  263s 414ms/step - loss: 1.1012 - sparse_categorical_accuracy: 0.5715


631/Unknown  264s 414ms/step - loss: 1.1008 - sparse_categorical_accuracy: 0.5716


632/Unknown  264s 414ms/step - loss: 1.1003 - sparse_categorical_accuracy: 0.5717


633/Unknown  265s 414ms/step - loss: 1.0999 - sparse_categorical_accuracy: 0.5719


634/Unknown  265s 414ms/step - loss: 1.0995 - sparse_categorical_accuracy: 0.5720


635/Unknown  265s 413ms/step - loss: 1.0991 - sparse_categorical_accuracy: 0.5722


636/Unknown  266s 413ms/step - loss: 1.0987 - sparse_categorical_accuracy: 0.5723


637/Unknown  266s 413ms/step - loss: 1.0982 - sparse_categorical_accuracy: 0.5724


638/Unknown  266s 413ms/step - loss: 1.0978 - sparse_categorical_accuracy: 0.5726


639/Unknown  267s 413ms/step - loss: 1.0974 - sparse_categorical_accuracy: 0.5727


640/Unknown  267s 413ms/step - loss: 1.0970 - sparse_categorical_accuracy: 0.5728


641/Unknown  268s 413ms/step - loss: 1.0966 - sparse_categorical_accuracy: 0.5730


642/Unknown  268s 413ms/step - loss: 1.0962 - sparse_categorical_accuracy: 0.5731


643/Unknown  268s 413ms/step - loss: 1.0957 - sparse_categorical_accuracy: 0.5733


644/Unknown  269s 413ms/step - loss: 1.0953 - sparse_categorical_accuracy: 0.5734


645/Unknown  269s 413ms/step - loss: 1.0949 - sparse_categorical_accuracy: 0.5735


646/Unknown  269s 413ms/step - loss: 1.0945 - sparse_categorical_accuracy: 0.5737


647/Unknown  270s 413ms/step - loss: 1.0941 - sparse_categorical_accuracy: 0.5738


648/Unknown  270s 413ms/step - loss: 1.0937 - sparse_categorical_accuracy: 0.5739


649/Unknown  270s 413ms/step - loss: 1.0933 - sparse_categorical_accuracy: 0.5741


650/Unknown  271s 413ms/step - loss: 1.0929 - sparse_categorical_accuracy: 0.5742


651/Unknown  271s 413ms/step - loss: 1.0925 - sparse_categorical_accuracy: 0.5743


652/Unknown  272s 412ms/step - loss: 1.0921 - sparse_categorical_accuracy: 0.5745


653/Unknown  272s 412ms/step - loss: 1.0917 - sparse_categorical_accuracy: 0.5746


654/Unknown  272s 412ms/step - loss: 1.0913 - sparse_categorical_accuracy: 0.5747


655/Unknown  273s 412ms/step - loss: 1.0909 - sparse_categorical_accuracy: 0.5749


656/Unknown  273s 412ms/step - loss: 1.0905 - sparse_categorical_accuracy: 0.5750


657/Unknown  274s 413ms/step - loss: 1.0901 - sparse_categorical_accuracy: 0.5751


658/Unknown  274s 413ms/step - loss: 1.0897 - sparse_categorical_accuracy: 0.5753


659/Unknown  275s 413ms/step - loss: 1.0893 - sparse_categorical_accuracy: 0.5754


660/Unknown  275s 413ms/step - loss: 1.0889 - sparse_categorical_accuracy: 0.5755


661/Unknown  275s 413ms/step - loss: 1.0885 - sparse_categorical_accuracy: 0.5757


662/Unknown  276s 413ms/step - loss: 1.0881 - sparse_categorical_accuracy: 0.5758


663/Unknown  276s 413ms/step - loss: 1.0877 - sparse_categorical_accuracy: 0.5759


664/Unknown  277s 413ms/step - loss: 1.0873 - sparse_categorical_accuracy: 0.5760


665/Unknown  277s 413ms/step - loss: 1.0869 - sparse_categorical_accuracy: 0.5762


666/Unknown  278s 413ms/step - loss: 1.0865 - sparse_categorical_accuracy: 0.5763


667/Unknown  278s 413ms/step - loss: 1.0861 - sparse_categorical_accuracy: 0.5764


668/Unknown  279s 413ms/step - loss: 1.0857 - sparse_categorical_accuracy: 0.5766


669/Unknown  279s 413ms/step - loss: 1.0853 - sparse_categorical_accuracy: 0.5767


670/Unknown  279s 413ms/step - loss: 1.0849 - sparse_categorical_accuracy: 0.5768


671/Unknown  280s 413ms/step - loss: 1.0845 - sparse_categorical_accuracy: 0.5770


672/Unknown  280s 413ms/step - loss: 1.0842 - sparse_categorical_accuracy: 0.5771


673/Unknown  281s 413ms/step - loss: 1.0838 - sparse_categorical_accuracy: 0.5772


674/Unknown  281s 413ms/step - loss: 1.0834 - sparse_categorical_accuracy: 0.5773


675/Unknown  281s 413ms/step - loss: 1.0830 - sparse_categorical_accuracy: 0.5775


676/Unknown  282s 413ms/step - loss: 1.0826 - sparse_categorical_accuracy: 0.5776


677/Unknown  282s 413ms/step - loss: 1.0822 - sparse_categorical_accuracy: 0.5777


678/Unknown  282s 412ms/step - loss: 1.0818 - sparse_categorical_accuracy: 0.5778


679/Unknown  283s 412ms/step - loss: 1.0815 - sparse_categorical_accuracy: 0.5780


680/Unknown  283s 412ms/step - loss: 1.0811 - sparse_categorical_accuracy: 0.5781


681/Unknown  284s 412ms/step - loss: 1.0807 - sparse_categorical_accuracy: 0.5782


682/Unknown  284s 412ms/step - loss: 1.0803 - sparse_categorical_accuracy: 0.5783


683/Unknown  284s 412ms/step - loss: 1.0799 - sparse_categorical_accuracy: 0.5785


684/Unknown  285s 412ms/step - loss: 1.0796 - sparse_categorical_accuracy: 0.5786


685/Unknown  285s 412ms/step - loss: 1.0792 - sparse_categorical_accuracy: 0.5787


686/Unknown  286s 412ms/step - loss: 1.0788 - sparse_categorical_accuracy: 0.5788


687/Unknown  286s 412ms/step - loss: 1.0784 - sparse_categorical_accuracy: 0.5790


688/Unknown  287s 413ms/step - loss: 1.0780 - sparse_categorical_accuracy: 0.5791


689/Unknown  287s 413ms/step - loss: 1.0777 - sparse_categorical_accuracy: 0.5792


690/Unknown  287s 413ms/step - loss: 1.0773 - sparse_categorical_accuracy: 0.5793


691/Unknown  288s 413ms/step - loss: 1.0769 - sparse_categorical_accuracy: 0.5795


692/Unknown  288s 413ms/step - loss: 1.0765 - sparse_categorical_accuracy: 0.5796


693/Unknown  289s 413ms/step - loss: 1.0762 - sparse_categorical_accuracy: 0.5797


694/Unknown  289s 413ms/step - loss: 1.0758 - sparse_categorical_accuracy: 0.5798


695/Unknown  290s 413ms/step - loss: 1.0754 - sparse_categorical_accuracy: 0.5800


696/Unknown  290s 413ms/step - loss: 1.0751 - sparse_categorical_accuracy: 0.5801


697/Unknown  291s 413ms/step - loss: 1.0747 - sparse_categorical_accuracy: 0.5802


698/Unknown  291s 413ms/step - loss: 1.0743 - sparse_categorical_accuracy: 0.5803


699/Unknown  292s 413ms/step - loss: 1.0740 - sparse_categorical_accuracy: 0.5804


700/Unknown  292s 413ms/step - loss: 1.0736 - sparse_categorical_accuracy: 0.5806


701/Unknown  292s 413ms/step - loss: 1.0732 - sparse_categorical_accuracy: 0.5807


702/Unknown  293s 413ms/step - loss: 1.0729 - sparse_categorical_accuracy: 0.5808


703/Unknown  293s 413ms/step - loss: 1.0725 - sparse_categorical_accuracy: 0.5809


704/Unknown  294s 413ms/step - loss: 1.0721 - sparse_categorical_accuracy: 0.5810


705/Unknown  294s 413ms/step - loss: 1.0718 - sparse_categorical_accuracy: 0.5812


706/Unknown  295s 413ms/step - loss: 1.0714 - sparse_categorical_accuracy: 0.5813


707/Unknown  295s 413ms/step - loss: 1.0710 - sparse_categorical_accuracy: 0.5814


708/Unknown  295s 413ms/step - loss: 1.0707 - sparse_categorical_accuracy: 0.5815


709/Unknown  296s 413ms/step - loss: 1.0703 - sparse_categorical_accuracy: 0.5816


710/Unknown  296s 413ms/step - loss: 1.0700 - sparse_categorical_accuracy: 0.5818


711/Unknown  296s 413ms/step - loss: 1.0696 - sparse_categorical_accuracy: 0.5819


712/Unknown  297s 413ms/step - loss: 1.0692 - sparse_categorical_accuracy: 0.5820


713/Unknown  297s 413ms/step - loss: 1.0689 - sparse_categorical_accuracy: 0.5821


714/Unknown  298s 413ms/step - loss: 1.0685 - sparse_categorical_accuracy: 0.5822


715/Unknown  298s 413ms/step - loss: 1.0682 - sparse_categorical_accuracy: 0.5824


716/Unknown  298s 413ms/step - loss: 1.0678 - sparse_categorical_accuracy: 0.5825


717/Unknown  299s 413ms/step - loss: 1.0675 - sparse_categorical_accuracy: 0.5826


718/Unknown  299s 413ms/step - loss: 1.0671 - sparse_categorical_accuracy: 0.5827


719/Unknown  300s 413ms/step - loss: 1.0668 - sparse_categorical_accuracy: 0.5828


720/Unknown  300s 413ms/step - loss: 1.0664 - sparse_categorical_accuracy: 0.5829


721/Unknown  300s 413ms/step - loss: 1.0661 - sparse_categorical_accuracy: 0.5831


722/Unknown  301s 413ms/step - loss: 1.0657 - sparse_categorical_accuracy: 0.5832


723/Unknown  301s 413ms/step - loss: 1.0653 - sparse_categorical_accuracy: 0.5833


724/Unknown  301s 413ms/step - loss: 1.0650 - sparse_categorical_accuracy: 0.5834


725/Unknown  302s 413ms/step - loss: 1.0646 - sparse_categorical_accuracy: 0.5835


726/Unknown  302s 413ms/step - loss: 1.0643 - sparse_categorical_accuracy: 0.5836


727/Unknown  303s 413ms/step - loss: 1.0640 - sparse_categorical_accuracy: 0.5837


728/Unknown  303s 413ms/step - loss: 1.0636 - sparse_categorical_accuracy: 0.5839


729/Unknown  304s 413ms/step - loss: 1.0633 - sparse_categorical_accuracy: 0.5840


730/Unknown  304s 413ms/step - loss: 1.0629 - sparse_categorical_accuracy: 0.5841


731/Unknown  305s 413ms/step - loss: 1.0626 - sparse_categorical_accuracy: 0.5842


732/Unknown  305s 413ms/step - loss: 1.0622 - sparse_categorical_accuracy: 0.5843


733/Unknown  305s 413ms/step - loss: 1.0619 - sparse_categorical_accuracy: 0.5844


734/Unknown  306s 413ms/step - loss: 1.0615 - sparse_categorical_accuracy: 0.5845


735/Unknown  306s 413ms/step - loss: 1.0612 - sparse_categorical_accuracy: 0.5847


736/Unknown  307s 413ms/step - loss: 1.0608 - sparse_categorical_accuracy: 0.5848


737/Unknown  307s 413ms/step - loss: 1.0605 - sparse_categorical_accuracy: 0.5849


738/Unknown  308s 413ms/step - loss: 1.0602 - sparse_categorical_accuracy: 0.5850


739/Unknown  308s 414ms/step - loss: 1.0598 - sparse_categorical_accuracy: 0.5851


740/Unknown  309s 414ms/step - loss: 1.0595 - sparse_categorical_accuracy: 0.5852


741/Unknown  309s 414ms/step - loss: 1.0591 - sparse_categorical_accuracy: 0.5853


742/Unknown  310s 414ms/step - loss: 1.0588 - sparse_categorical_accuracy: 0.5854


743/Unknown  310s 414ms/step - loss: 1.0585 - sparse_categorical_accuracy: 0.5856


744/Unknown  310s 414ms/step - loss: 1.0581 - sparse_categorical_accuracy: 0.5857


745/Unknown  311s 414ms/step - loss: 1.0578 - sparse_categorical_accuracy: 0.5858


746/Unknown  311s 413ms/step - loss: 1.0575 - sparse_categorical_accuracy: 0.5859


747/Unknown  312s 413ms/step - loss: 1.0571 - sparse_categorical_accuracy: 0.5860


748/Unknown  312s 413ms/step - loss: 1.0568 - sparse_categorical_accuracy: 0.5861


749/Unknown  312s 413ms/step - loss: 1.0565 - sparse_categorical_accuracy: 0.5862


750/Unknown  313s 413ms/step - loss: 1.0561 - sparse_categorical_accuracy: 0.5863


751/Unknown  313s 413ms/step - loss: 1.0558 - sparse_categorical_accuracy: 0.5864


752/Unknown  313s 413ms/step - loss: 1.0555 - sparse_categorical_accuracy: 0.5866


753/Unknown  314s 413ms/step - loss: 1.0551 - sparse_categorical_accuracy: 0.5867


754/Unknown  314s 413ms/step - loss: 1.0548 - sparse_categorical_accuracy: 0.5868


755/Unknown  314s 413ms/step - loss: 1.0545 - sparse_categorical_accuracy: 0.5869


756/Unknown  315s 413ms/step - loss: 1.0541 - sparse_categorical_accuracy: 0.5870


757/Unknown  315s 413ms/step - loss: 1.0538 - sparse_categorical_accuracy: 0.5871


758/Unknown  316s 413ms/step - loss: 1.0535 - sparse_categorical_accuracy: 0.5872


759/Unknown  316s 413ms/step - loss: 1.0531 - sparse_categorical_accuracy: 0.5873


760/Unknown  317s 413ms/step - loss: 1.0528 - sparse_categorical_accuracy: 0.5874


761/Unknown  317s 413ms/step - loss: 1.0525 - sparse_categorical_accuracy: 0.5875


762/Unknown  318s 413ms/step - loss: 1.0522 - sparse_categorical_accuracy: 0.5876


763/Unknown  318s 413ms/step - loss: 1.0518 - sparse_categorical_accuracy: 0.5877


764/Unknown  319s 413ms/step - loss: 1.0515 - sparse_categorical_accuracy: 0.5879


765/Unknown  319s 413ms/step - loss: 1.0512 - sparse_categorical_accuracy: 0.5880


766/Unknown  319s 413ms/step - loss: 1.0509 - sparse_categorical_accuracy: 0.5881


767/Unknown  320s 414ms/step - loss: 1.0505 - sparse_categorical_accuracy: 0.5882


768/Unknown  320s 414ms/step - loss: 1.0502 - sparse_categorical_accuracy: 0.5883


769/Unknown  321s 414ms/step - loss: 1.0499 - sparse_categorical_accuracy: 0.5884


770/Unknown  321s 414ms/step - loss: 1.0496 - sparse_categorical_accuracy: 0.5885


771/Unknown  322s 414ms/step - loss: 1.0493 - sparse_categorical_accuracy: 0.5886


772/Unknown  322s 414ms/step - loss: 1.0489 - sparse_categorical_accuracy: 0.5887


773/Unknown  322s 414ms/step - loss: 1.0486 - sparse_categorical_accuracy: 0.5888


774/Unknown  323s 414ms/step - loss: 1.0483 - sparse_categorical_accuracy: 0.5889


775/Unknown  323s 413ms/step - loss: 1.0480 - sparse_categorical_accuracy: 0.5890


776/Unknown  323s 413ms/step - loss: 1.0477 - sparse_categorical_accuracy: 0.5891


777/Unknown  324s 413ms/step - loss: 1.0473 - sparse_categorical_accuracy: 0.5892


778/Unknown  324s 413ms/step - loss: 1.0470 - sparse_categorical_accuracy: 0.5893


779/Unknown  325s 413ms/step - loss: 1.0467 - sparse_categorical_accuracy: 0.5894


780/Unknown  325s 413ms/step - loss: 1.0464 - sparse_categorical_accuracy: 0.5895


781/Unknown  325s 413ms/step - loss: 1.0461 - sparse_categorical_accuracy: 0.5896


782/Unknown  326s 413ms/step - loss: 1.0458 - sparse_categorical_accuracy: 0.5898


783/Unknown  326s 413ms/step - loss: 1.0454 - sparse_categorical_accuracy: 0.5899


784/Unknown  327s 413ms/step - loss: 1.0451 - sparse_categorical_accuracy: 0.5900


785/Unknown  327s 413ms/step - loss: 1.0448 - sparse_categorical_accuracy: 0.5901


786/Unknown  327s 413ms/step - loss: 1.0445 - sparse_categorical_accuracy: 0.5902


787/Unknown  328s 413ms/step - loss: 1.0442 - sparse_categorical_accuracy: 0.5903


788/Unknown  328s 413ms/step - loss: 1.0439 - sparse_categorical_accuracy: 0.5904


789/Unknown  329s 413ms/step - loss: 1.0436 - sparse_categorical_accuracy: 0.5905


790/Unknown  329s 413ms/step - loss: 1.0433 - sparse_categorical_accuracy: 0.5906


791/Unknown  330s 413ms/step - loss: 1.0429 - sparse_categorical_accuracy: 0.5907


792/Unknown  330s 413ms/step - loss: 1.0426 - sparse_categorical_accuracy: 0.5908


793/Unknown  331s 413ms/step - loss: 1.0423 - sparse_categorical_accuracy: 0.5909


794/Unknown  331s 414ms/step - loss: 1.0420 - sparse_categorical_accuracy: 0.5910


795/Unknown  331s 414ms/step - loss: 1.0417 - sparse_categorical_accuracy: 0.5911


796/Unknown  332s 414ms/step - loss: 1.0414 - sparse_categorical_accuracy: 0.5912


797/Unknown  332s 414ms/step - loss: 1.0411 - sparse_categorical_accuracy: 0.5913


798/Unknown  333s 414ms/step - loss: 1.0408 - sparse_categorical_accuracy: 0.5914


799/Unknown  333s 413ms/step - loss: 1.0405 - sparse_categorical_accuracy: 0.5915


800/Unknown  334s 414ms/step - loss: 1.0402 - sparse_categorical_accuracy: 0.5916


801/Unknown  334s 414ms/step - loss: 1.0399 - sparse_categorical_accuracy: 0.5917


802/Unknown  334s 414ms/step - loss: 1.0396 - sparse_categorical_accuracy: 0.5918


803/Unknown  335s 414ms/step - loss: 1.0393 - sparse_categorical_accuracy: 0.5919


804/Unknown  335s 413ms/step - loss: 1.0390 - sparse_categorical_accuracy: 0.5920


805/Unknown  335s 413ms/step - loss: 1.0387 - sparse_categorical_accuracy: 0.5921


806/Unknown  336s 413ms/step - loss: 1.0384 - sparse_categorical_accuracy: 0.5922


807/Unknown  336s 413ms/step - loss: 1.0381 - sparse_categorical_accuracy: 0.5923


808/Unknown  336s 413ms/step - loss: 1.0378 - sparse_categorical_accuracy: 0.5924


809/Unknown  337s 413ms/step - loss: 1.0375 - sparse_categorical_accuracy: 0.5925


810/Unknown  337s 413ms/step - loss: 1.0372 - sparse_categorical_accuracy: 0.5926


811/Unknown  338s 413ms/step - loss: 1.0369 - sparse_categorical_accuracy: 0.5927


812/Unknown  338s 413ms/step - loss: 1.0366 - sparse_categorical_accuracy: 0.5928


813/Unknown  338s 413ms/step - loss: 1.0363 - sparse_categorical_accuracy: 0.5929


814/Unknown  339s 413ms/step - loss: 1.0360 - sparse_categorical_accuracy: 0.5930


815/Unknown  339s 413ms/step - loss: 1.0357 - sparse_categorical_accuracy: 0.5931


816/Unknown  339s 413ms/step - loss: 1.0354 - sparse_categorical_accuracy: 0.5932


817/Unknown  340s 413ms/step - loss: 1.0351 - sparse_categorical_accuracy: 0.5933


818/Unknown  340s 413ms/step - loss: 1.0348 - sparse_categorical_accuracy: 0.5934


819/Unknown  341s 413ms/step - loss: 1.0345 - sparse_categorical_accuracy: 0.5935


820/Unknown  341s 412ms/step - loss: 1.0342 - sparse_categorical_accuracy: 0.5936


821/Unknown  341s 412ms/step - loss: 1.0339 - sparse_categorical_accuracy: 0.5937


822/Unknown  342s 412ms/step - loss: 1.0336 - sparse_categorical_accuracy: 0.5938


823/Unknown  342s 412ms/step - loss: 1.0333 - sparse_categorical_accuracy: 0.5939


824/Unknown  343s 412ms/step - loss: 1.0330 - sparse_categorical_accuracy: 0.5939


825/Unknown  343s 412ms/step - loss: 1.0327 - sparse_categorical_accuracy: 0.5940


826/Unknown  343s 412ms/step - loss: 1.0324 - sparse_categorical_accuracy: 0.5941


827/Unknown  344s 412ms/step - loss: 1.0322 - sparse_categorical_accuracy: 0.5942


828/Unknown  344s 412ms/step - loss: 1.0319 - sparse_categorical_accuracy: 0.5943


829/Unknown  344s 412ms/step - loss: 1.0316 - sparse_categorical_accuracy: 0.5944


830/Unknown  345s 412ms/step - loss: 1.0313 - sparse_categorical_accuracy: 0.5945


831/Unknown  345s 412ms/step - loss: 1.0310 - sparse_categorical_accuracy: 0.5946


832/Unknown  346s 412ms/step - loss: 1.0307 - sparse_categorical_accuracy: 0.5947


833/Unknown  346s 412ms/step - loss: 1.0304 - sparse_categorical_accuracy: 0.5948


834/Unknown  346s 412ms/step - loss: 1.0301 - sparse_categorical_accuracy: 0.5949


835/Unknown  347s 412ms/step - loss: 1.0298 - sparse_categorical_accuracy: 0.5950


836/Unknown  347s 412ms/step - loss: 1.0296 - sparse_categorical_accuracy: 0.5951


837/Unknown  348s 412ms/step - loss: 1.0293 - sparse_categorical_accuracy: 0.5952


838/Unknown  348s 412ms/step - loss: 1.0290 - sparse_categorical_accuracy: 0.5953


839/Unknown  348s 412ms/step - loss: 1.0287 - sparse_categorical_accuracy: 0.5954


840/Unknown  349s 412ms/step - loss: 1.0284 - sparse_categorical_accuracy: 0.5955


841/Unknown  349s 412ms/step - loss: 1.0281 - sparse_categorical_accuracy: 0.5956


842/Unknown  350s 412ms/step - loss: 1.0278 - sparse_categorical_accuracy: 0.5957


843/Unknown  350s 412ms/step - loss: 1.0276 - sparse_categorical_accuracy: 0.5958


844/Unknown  351s 412ms/step - loss: 1.0273 - sparse_categorical_accuracy: 0.5958


845/Unknown  351s 412ms/step - loss: 1.0270 - sparse_categorical_accuracy: 0.5959


846/Unknown  352s 412ms/step - loss: 1.0267 - sparse_categorical_accuracy: 0.5960


847/Unknown  352s 412ms/step - loss: 1.0264 - sparse_categorical_accuracy: 0.5961


848/Unknown  352s 412ms/step - loss: 1.0261 - sparse_categorical_accuracy: 0.5962


849/Unknown  353s 412ms/step - loss: 1.0259 - sparse_categorical_accuracy: 0.5963


850/Unknown  353s 412ms/step - loss: 1.0256 - sparse_categorical_accuracy: 0.5964


851/Unknown  354s 412ms/step - loss: 1.0253 - sparse_categorical_accuracy: 0.5965


852/Unknown  354s 412ms/step - loss: 1.0250 - sparse_categorical_accuracy: 0.5966


853/Unknown  354s 412ms/step - loss: 1.0247 - sparse_categorical_accuracy: 0.5967


854/Unknown  355s 412ms/step - loss: 1.0245 - sparse_categorical_accuracy: 0.5968


855/Unknown  355s 412ms/step - loss: 1.0242 - sparse_categorical_accuracy: 0.5969


856/Unknown  355s 412ms/step - loss: 1.0239 - sparse_categorical_accuracy: 0.5970


857/Unknown  356s 412ms/step - loss: 1.0236 - sparse_categorical_accuracy: 0.5970


858/Unknown  356s 412ms/step - loss: 1.0234 - sparse_categorical_accuracy: 0.5971


859/Unknown  357s 412ms/step - loss: 1.0231 - sparse_categorical_accuracy: 0.5972


860/Unknown  357s 412ms/step - loss: 1.0228 - sparse_categorical_accuracy: 0.5973


861/Unknown  357s 412ms/step - loss: 1.0225 - sparse_categorical_accuracy: 0.5974


862/Unknown  358s 412ms/step - loss: 1.0223 - sparse_categorical_accuracy: 0.5975


863/Unknown  358s 412ms/step - loss: 1.0220 - sparse_categorical_accuracy: 0.5976


864/Unknown  359s 412ms/step - loss: 1.0217 - sparse_categorical_accuracy: 0.5977


865/Unknown  359s 412ms/step - loss: 1.0214 - sparse_categorical_accuracy: 0.5978


866/Unknown  360s 412ms/step - loss: 1.0212 - sparse_categorical_accuracy: 0.5979


867/Unknown  360s 412ms/step - loss: 1.0209 - sparse_categorical_accuracy: 0.5980


868/Unknown  361s 412ms/step - loss: 1.0206 - sparse_categorical_accuracy: 0.5980


869/Unknown  361s 412ms/step - loss: 1.0203 - sparse_categorical_accuracy: 0.5981


870/Unknown  361s 412ms/step - loss: 1.0201 - sparse_categorical_accuracy: 0.5982


871/Unknown  362s 412ms/step - loss: 1.0198 - sparse_categorical_accuracy: 0.5983


872/Unknown  362s 412ms/step - loss: 1.0195 - sparse_categorical_accuracy: 0.5984


873/Unknown  363s 412ms/step - loss: 1.0193 - sparse_categorical_accuracy: 0.5985


874/Unknown  363s 412ms/step - loss: 1.0190 - sparse_categorical_accuracy: 0.5986


875/Unknown  364s 412ms/step - loss: 1.0187 - sparse_categorical_accuracy: 0.5987


876/Unknown  364s 412ms/step - loss: 1.0184 - sparse_categorical_accuracy: 0.5988


877/Unknown  364s 412ms/step - loss: 1.0182 - sparse_categorical_accuracy: 0.5988


878/Unknown  365s 412ms/step - loss: 1.0179 - sparse_categorical_accuracy: 0.5989


879/Unknown  365s 412ms/step - loss: 1.0176 - sparse_categorical_accuracy: 0.5990


880/Unknown  365s 412ms/step - loss: 1.0174 - sparse_categorical_accuracy: 0.5991


881/Unknown  366s 412ms/step - loss: 1.0171 - sparse_categorical_accuracy: 0.5992


882/Unknown  366s 412ms/step - loss: 1.0168 - sparse_categorical_accuracy: 0.5993


883/Unknown  367s 412ms/step - loss: 1.0166 - sparse_categorical_accuracy: 0.5994


884/Unknown  367s 412ms/step - loss: 1.0163 - sparse_categorical_accuracy: 0.5995


885/Unknown  367s 412ms/step - loss: 1.0160 - sparse_categorical_accuracy: 0.5996


886/Unknown  368s 412ms/step - loss: 1.0158 - sparse_categorical_accuracy: 0.5996


887/Unknown  368s 412ms/step - loss: 1.0155 - sparse_categorical_accuracy: 0.5997


888/Unknown  368s 412ms/step - loss: 1.0153 - sparse_categorical_accuracy: 0.5998


889/Unknown  369s 412ms/step - loss: 1.0150 - sparse_categorical_accuracy: 0.5999


890/Unknown  369s 412ms/step - loss: 1.0147 - sparse_categorical_accuracy: 0.6000


891/Unknown  370s 412ms/step - loss: 1.0145 - sparse_categorical_accuracy: 0.6001


892/Unknown  370s 412ms/step - loss: 1.0142 - sparse_categorical_accuracy: 0.6002


893/Unknown  371s 412ms/step - loss: 1.0139 - sparse_categorical_accuracy: 0.6002


894/Unknown  371s 412ms/step - loss: 1.0137 - sparse_categorical_accuracy: 0.6003


895/Unknown  371s 412ms/step - loss: 1.0134 - sparse_categorical_accuracy: 0.6004


896/Unknown  372s 412ms/step - loss: 1.0132 - sparse_categorical_accuracy: 0.6005


897/Unknown  372s 412ms/step - loss: 1.0129 - sparse_categorical_accuracy: 0.6006


898/Unknown  373s 412ms/step - loss: 1.0126 - sparse_categorical_accuracy: 0.6007


899/Unknown  373s 412ms/step - loss: 1.0124 - sparse_categorical_accuracy: 0.6008


900/Unknown  373s 412ms/step - loss: 1.0121 - sparse_categorical_accuracy: 0.6008


901/Unknown  374s 412ms/step - loss: 1.0119 - sparse_categorical_accuracy: 0.6009


902/Unknown  374s 412ms/step - loss: 1.0116 - sparse_categorical_accuracy: 0.6010


903/Unknown  374s 412ms/step - loss: 1.0113 - sparse_categorical_accuracy: 0.6011


904/Unknown  375s 412ms/step - loss: 1.0111 - sparse_categorical_accuracy: 0.6012


905/Unknown  375s 412ms/step - loss: 1.0108 - sparse_categorical_accuracy: 0.6013


906/Unknown  376s 412ms/step - loss: 1.0106 - sparse_categorical_accuracy: 0.6014


907/Unknown  376s 412ms/step - loss: 1.0103 - sparse_categorical_accuracy: 0.6014


908/Unknown  376s 412ms/step - loss: 1.0101 - sparse_categorical_accuracy: 0.6015


909/Unknown  377s 411ms/step - loss: 1.0098 - sparse_categorical_accuracy: 0.6016


910/Unknown  377s 411ms/step - loss: 1.0096 - sparse_categorical_accuracy: 0.6017


911/Unknown  378s 411ms/step - loss: 1.0093 - sparse_categorical_accuracy: 0.6018


912/Unknown  378s 411ms/step - loss: 1.0091 - sparse_categorical_accuracy: 0.6019


913/Unknown  378s 411ms/step - loss: 1.0088 - sparse_categorical_accuracy: 0.6019


914/Unknown  379s 411ms/step - loss: 1.0085 - sparse_categorical_accuracy: 0.6020


915/Unknown  379s 411ms/step - loss: 1.0083 - sparse_categorical_accuracy: 0.6021


916/Unknown  380s 412ms/step - loss: 1.0080 - sparse_categorical_accuracy: 0.6022


917/Unknown  380s 412ms/step - loss: 1.0078 - sparse_categorical_accuracy: 0.6023


918/Unknown  380s 412ms/step - loss: 1.0075 - sparse_categorical_accuracy: 0.6024


919/Unknown  381s 411ms/step - loss: 1.0073 - sparse_categorical_accuracy: 0.6024


920/Unknown  381s 411ms/step - loss: 1.0070 - sparse_categorical_accuracy: 0.6025


921/Unknown  382s 411ms/step - loss: 1.0068 - sparse_categorical_accuracy: 0.6026


922/Unknown  382s 411ms/step - loss: 1.0065 - sparse_categorical_accuracy: 0.6027


923/Unknown  382s 411ms/step - loss: 1.0063 - sparse_categorical_accuracy: 0.6028


924/Unknown  383s 411ms/step - loss: 1.0060 - sparse_categorical_accuracy: 0.6029


925/Unknown  383s 411ms/step - loss: 1.0058 - sparse_categorical_accuracy: 0.6029


926/Unknown  383s 411ms/step - loss: 1.0055 - sparse_categorical_accuracy: 0.6030


927/Unknown  384s 411ms/step - loss: 1.0053 - sparse_categorical_accuracy: 0.6031


928/Unknown  384s 411ms/step - loss: 1.0051 - sparse_categorical_accuracy: 0.6032


929/Unknown  384s 411ms/step - loss: 1.0048 - sparse_categorical_accuracy: 0.6033


930/Unknown  385s 411ms/step - loss: 1.0046 - sparse_categorical_accuracy: 0.6033


931/Unknown  385s 411ms/step - loss: 1.0043 - sparse_categorical_accuracy: 0.6034


932/Unknown  386s 411ms/step - loss: 1.0041 - sparse_categorical_accuracy: 0.6035


933/Unknown  386s 411ms/step - loss: 1.0038 - sparse_categorical_accuracy: 0.6036


934/Unknown  386s 411ms/step - loss: 1.0036 - sparse_categorical_accuracy: 0.6037


935/Unknown  387s 411ms/step - loss: 1.0033 - sparse_categorical_accuracy: 0.6037


936/Unknown  387s 411ms/step - loss: 1.0031 - sparse_categorical_accuracy: 0.6038


937/Unknown  387s 411ms/step - loss: 1.0028 - sparse_categorical_accuracy: 0.6039


938/Unknown  388s 411ms/step - loss: 1.0026 - sparse_categorical_accuracy: 0.6040


939/Unknown  388s 411ms/step - loss: 1.0024 - sparse_categorical_accuracy: 0.6041


940/Unknown  389s 411ms/step - loss: 1.0021 - sparse_categorical_accuracy: 0.6042


941/Unknown  389s 410ms/step - loss: 1.0019 - sparse_categorical_accuracy: 0.6042


942/Unknown  389s 410ms/step - loss: 1.0016 - sparse_categorical_accuracy: 0.6043


943/Unknown  390s 411ms/step - loss: 1.0014 - sparse_categorical_accuracy: 0.6044


944/Unknown  390s 411ms/step - loss: 1.0011 - sparse_categorical_accuracy: 0.6045


945/Unknown  391s 411ms/step - loss: 1.0009 - sparse_categorical_accuracy: 0.6046


946/Unknown  391s 411ms/step - loss: 1.0007 - sparse_categorical_accuracy: 0.6046


947/Unknown  392s 411ms/step - loss: 1.0004 - sparse_categorical_accuracy: 0.6047


948/Unknown  392s 411ms/step - loss: 1.0002 - sparse_categorical_accuracy: 0.6048


949/Unknown  393s 411ms/step - loss: 0.9999 - sparse_categorical_accuracy: 0.6049


950/Unknown  393s 411ms/step - loss: 0.9997 - sparse_categorical_accuracy: 0.6049


951/Unknown  393s 411ms/step - loss: 0.9995 - sparse_categorical_accuracy: 0.6050


952/Unknown  394s 411ms/step - loss: 0.9992 - sparse_categorical_accuracy: 0.6051


953/Unknown  394s 411ms/step - loss: 0.9990 - sparse_categorical_accuracy: 0.6052


954/Unknown  394s 411ms/step - loss: 0.9988 - sparse_categorical_accuracy: 0.6053


955/Unknown  395s 410ms/step - loss: 0.9985 - sparse_categorical_accuracy: 0.6053


956/Unknown  395s 410ms/step - loss: 0.9983 - sparse_categorical_accuracy: 0.6054


957/Unknown  395s 410ms/step - loss: 0.9980 - sparse_categorical_accuracy: 0.6055


958/Unknown  396s 410ms/step - loss: 0.9978 - sparse_categorical_accuracy: 0.6056


959/Unknown  396s 410ms/step - loss: 0.9976 - sparse_categorical_accuracy: 0.6057


960/Unknown  397s 410ms/step - loss: 0.9973 - sparse_categorical_accuracy: 0.6057


961/Unknown  397s 410ms/step - loss: 0.9971 - sparse_categorical_accuracy: 0.6058


962/Unknown  397s 410ms/step - loss: 0.9969 - sparse_categorical_accuracy: 0.6059


963/Unknown  398s 410ms/step - loss: 0.9966 - sparse_categorical_accuracy: 0.6060


964/Unknown  398s 410ms/step - loss: 0.9964 - sparse_categorical_accuracy: 0.6060


965/Unknown  398s 410ms/step - loss: 0.9962 - sparse_categorical_accuracy: 0.6061


966/Unknown  399s 410ms/step - loss: 0.9959 - sparse_categorical_accuracy: 0.6062


967/Unknown  399s 410ms/step - loss: 0.9957 - sparse_categorical_accuracy: 0.6063


968/Unknown  400s 410ms/step - loss: 0.9955 - sparse_categorical_accuracy: 0.6064


969/Unknown  400s 410ms/step - loss: 0.9952 - sparse_categorical_accuracy: 0.6064


970/Unknown  401s 410ms/step - loss: 0.9950 - sparse_categorical_accuracy: 0.6065


971/Unknown  401s 410ms/step - loss: 0.9948 - sparse_categorical_accuracy: 0.6066


972/Unknown  402s 410ms/step - loss: 0.9945 - sparse_categorical_accuracy: 0.6067


973/Unknown  402s 410ms/step - loss: 0.9943 - sparse_categorical_accuracy: 0.6067


974/Unknown  402s 410ms/step - loss: 0.9941 - sparse_categorical_accuracy: 0.6068


975/Unknown  403s 410ms/step - loss: 0.9938 - sparse_categorical_accuracy: 0.6069


976/Unknown  403s 410ms/step - loss: 0.9936 - sparse_categorical_accuracy: 0.6070


977/Unknown  404s 410ms/step - loss: 0.9934 - sparse_categorical_accuracy: 0.6070


978/Unknown  404s 410ms/step - loss: 0.9931 - sparse_categorical_accuracy: 0.6071


979/Unknown  404s 410ms/step - loss: 0.9929 - sparse_categorical_accuracy: 0.6072


980/Unknown  405s 410ms/step - loss: 0.9927 - sparse_categorical_accuracy: 0.6073


981/Unknown  405s 410ms/step - loss: 0.9925 - sparse_categorical_accuracy: 0.6073


982/Unknown  405s 410ms/step - loss: 0.9922 - sparse_categorical_accuracy: 0.6074


983/Unknown  406s 410ms/step - loss: 0.9920 - sparse_categorical_accuracy: 0.6075


984/Unknown  406s 410ms/step - loss: 0.9918 - sparse_categorical_accuracy: 0.6076


985/Unknown  406s 410ms/step - loss: 0.9915 - sparse_categorical_accuracy: 0.6076


986/Unknown  407s 410ms/step - loss: 0.9913 - sparse_categorical_accuracy: 0.6077


987/Unknown  407s 410ms/step - loss: 0.9911 - sparse_categorical_accuracy: 0.6078


988/Unknown  408s 410ms/step - loss: 0.9909 - sparse_categorical_accuracy: 0.6079


989/Unknown  408s 410ms/step - loss: 0.9906 - sparse_categorical_accuracy: 0.6079


990/Unknown  408s 410ms/step - loss: 0.9904 - sparse_categorical_accuracy: 0.6080


991/Unknown  409s 410ms/step - loss: 0.9902 - sparse_categorical_accuracy: 0.6081


992/Unknown  409s 410ms/step - loss: 0.9900 - sparse_categorical_accuracy: 0.6082


993/Unknown  410s 410ms/step - loss: 0.9897 - sparse_categorical_accuracy: 0.6082


994/Unknown  410s 410ms/step - loss: 0.9895 - sparse_categorical_accuracy: 0.6083


995/Unknown  411s 410ms/step - loss: 0.9893 - sparse_categorical_accuracy: 0.6084


996/Unknown  411s 410ms/step - loss: 0.9891 - sparse_categorical_accuracy: 0.6085


997/Unknown  411s 410ms/step - loss: 0.9888 - sparse_categorical_accuracy: 0.6085


998/Unknown  412s 410ms/step - loss: 0.9886 - sparse_categorical_accuracy: 0.6086


999/Unknown  412s 410ms/step - loss: 0.9884 - sparse_categorical_accuracy: 0.6087

1000/未知 413秒 410毫秒/步 - loss: 0.9882 - sparse_categorical_accuracy: 0.6088

1001/未知 413秒 410毫秒/步 - loss: 0.9880 - sparse_categorical_accuracy: 0.6088

1002/未知 414秒 410毫秒/步 - loss: 0.9877 - sparse_categorical_accuracy: 0.6089

1003/未知 414秒 410毫秒/步 - loss: 0.9875 - sparse_categorical_accuracy: 0.6090

1004/未知 414秒 410毫秒/步 - loss: 0.9873 - sparse_categorical_accuracy: 0.6091

1005/未知 415秒 410毫秒/步 - loss: 0.9871 - sparse_categorical_accuracy: 0.6091

1006/未知 415秒 410毫秒/步 - loss: 0.9868 - sparse_categorical_accuracy: 0.6092

1007/未知 416秒 410毫秒/步 - loss: 0.9866 - sparse_categorical_accuracy: 0.6093

1008/未知 416秒 410毫秒/步 - loss: 0.9864 - sparse_categorical_accuracy: 0.6093

1009/未知 416秒 410毫秒/步 - loss: 0.9862 - sparse_categorical_accuracy: 0.6094

1010/未知 416秒 410毫秒/步 - loss: 0.9860 - sparse_categorical_accuracy: 0.6095

1011/未知 417秒 410毫秒/步 - loss: 0.9857 - sparse_categorical_accuracy: 0.6096

1012/未知 417秒 409毫秒/步 - loss: 0.9855 - sparse_categorical_accuracy: 0.6096

1013/未知 417秒 409毫秒/步 - loss: 0.9853 - sparse_categorical_accuracy: 0.6097

1014/未知 418秒 409毫秒/步 - loss: 0.9851 - sparse_categorical_accuracy: 0.6098

1015/未知 418秒 409毫秒/步 - loss: 0.9849 - sparse_categorical_accuracy: 0.6099

1016/未知 418秒 409毫秒/步 - loss: 0.9847 - sparse_categorical_accuracy: 0.6099

1017/未知 419秒 409毫秒/步 - loss: 0.9844 - sparse_categorical_accuracy: 0.6100

1018/未知 419秒 409毫秒/步 - loss: 0.9842 - sparse_categorical_accuracy: 0.6101

1019/未知 419秒 409毫秒/步 - loss: 0.9840 - sparse_categorical_accuracy: 0.6101

1020/未知 420秒 409毫秒/步 - loss: 0.9838 - sparse_categorical_accuracy: 0.6102

1021/未知 420秒 409毫秒/步 - loss: 0.9836 - sparse_categorical_accuracy: 0.6103

1022/未知 421秒 409毫秒/步 - loss: 0.9834 - sparse_categorical_accuracy: 0.6104

1023/未知 421秒 409毫秒/步 - loss: 0.9831 - sparse_categorical_accuracy: 0.6104

1024/未知 422秒 409毫秒/步 - loss: 0.9829 - sparse_categorical_accuracy: 0.6105

1025/未知 422秒 409毫秒/步 - loss: 0.9827 - sparse_categorical_accuracy: 0.6106

1026/未知 423秒 409毫秒/步 - loss: 0.9825 - sparse_categorical_accuracy: 0.6106

1027/未知 423秒 409毫秒/步 - loss: 0.9823 - sparse_categorical_accuracy: 0.6107

1028/未知 423秒 409毫秒/步 - loss: 0.9821 - sparse_categorical_accuracy: 0.6108

1029/未知 424秒 409毫秒/步 - loss: 0.9819 - sparse_categorical_accuracy: 0.6109

1030/未知 424秒 409毫秒/步 - loss: 0.9816 - sparse_categorical_accuracy: 0.6109

1031/未知 425秒 409毫秒/步 - loss: 0.9814 - sparse_categorical_accuracy: 0.6110

1032/未知 425秒 409毫秒/步 - loss: 0.9812 - sparse_categorical_accuracy: 0.6111

1033/未知 425秒 409毫秒/步 - loss: 0.9810 - sparse_categorical_accuracy: 0.6111

1034/未知 426秒 409毫秒/步 - loss: 0.9808 - sparse_categorical_accuracy: 0.6112

1035/未知 426秒 409毫秒/步 - loss: 0.9806 - sparse_categorical_accuracy: 0.6113

1036/未知 427秒 409毫秒/步 - loss: 0.9804 - sparse_categorical_accuracy: 0.6113

1037/未知 427秒 409毫秒/步 - loss: 0.9802 - sparse_categorical_accuracy: 0.6114

1038/未知 427秒 409毫秒/步 - loss: 0.9799 - sparse_categorical_accuracy: 0.6115

1039/未知 428秒 409毫秒/步 - loss: 0.9797 - sparse_categorical_accuracy: 0.6116

1040/未知 428秒 409毫秒/步 - loss: 0.9795 - sparse_categorical_accuracy: 0.6116

1041/未知 428秒 409毫秒/步 - loss: 0.9793 - sparse_categorical_accuracy: 0.6117

1042/未知 429秒 409毫秒/步 - loss: 0.9791 - sparse_categorical_accuracy: 0.6118

1043/未知 429秒 409毫秒/步 - loss: 0.9789 - sparse_categorical_accuracy: 0.6118

1044/未知 430秒 409毫秒/步 - loss: 0.9787 - sparse_categorical_accuracy: 0.6119

1045/未知 430秒 409毫秒/步 - loss: 0.9785 - sparse_categorical_accuracy: 0.6120

1046/未知 430秒 409毫秒/步 - loss: 0.9783 - sparse_categorical_accuracy: 0.6120

1047/未知 431秒 409毫秒/步 - loss: 0.9781 - sparse_categorical_accuracy: 0.6121

1048/未知 431秒 409毫秒/步 - loss: 0.9779 - sparse_categorical_accuracy: 0.6122

1049/未知 432秒 409毫秒/步 - loss: 0.9777 - sparse_categorical_accuracy: 0.6122

1050/未知 432秒 409毫秒/步 - loss: 0.9774 - sparse_categorical_accuracy: 0.6123

1051/未知 433秒 409毫秒/步 - loss: 0.9772 - sparse_categorical_accuracy: 0.6124

1052/未知 433秒 409毫秒/步 - loss: 0.9770 - sparse_categorical_accuracy: 0.6125

1053/未知 433秒 409毫秒/步 - loss: 0.9768 - sparse_categorical_accuracy: 0.6125

1054/未知 434秒 409毫秒/步 - loss: 0.9766 - sparse_categorical_accuracy: 0.6126

1055/未知 434秒 409毫秒/步 - loss: 0.9764 - sparse_categorical_accuracy: 0.6127

1056/未知 435秒 409毫秒/步 - loss: 0.9762 - sparse_categorical_accuracy: 0.6127

1057/未知 435秒 409毫秒/步 - loss: 0.9760 - sparse_categorical_accuracy: 0.6128

1058/未知 435秒 409毫秒/步 - loss: 0.9758 - sparse_categorical_accuracy: 0.6129

1059/未知 436秒 409毫秒/步 - loss: 0.9756 - sparse_categorical_accuracy: 0.6129

1060/未知 436秒 409毫秒/步 - loss: 0.9754 - sparse_categorical_accuracy: 0.6130

1061/未知 436秒 409毫秒/步 - loss: 0.9752 - sparse_categorical_accuracy: 0.6131

1062/未知 437秒 409毫秒/步 - loss: 0.9750 - sparse_categorical_accuracy: 0.6131

1063/未知 437秒 409毫秒/步 - loss: 0.9748 - sparse_categorical_accuracy: 0.6132

1064/未知 438秒 409毫秒/步 - loss: 0.9746 - sparse_categorical_accuracy: 0.6133

1065/未知 438秒 409毫秒/步 - loss: 0.9744 - sparse_categorical_accuracy: 0.6133

1066/未知 439秒 409毫秒/步 - loss: 0.9742 - sparse_categorical_accuracy: 0.6134

1067/未知 439秒 409毫秒/步 - loss: 0.9740 - sparse_categorical_accuracy: 0.6135

1068/未知 440秒 409毫秒/步 - loss: 0.9738 - sparse_categorical_accuracy: 0.6135

1069/未知 440秒 409毫秒/步 - loss: 0.9736 - sparse_categorical_accuracy: 0.6136

1070/未知 441秒 409毫秒/步 - loss: 0.9734 - sparse_categorical_accuracy: 0.6137

1071/未知 441秒 409毫秒/步 - loss: 0.9732 - sparse_categorical_accuracy: 0.6137

1072/未知 442秒 409毫秒/步 - loss: 0.9730 - sparse_categorical_accuracy: 0.6138

1073/未知 442秒 409毫秒/步 - loss: 0.9728 - sparse_categorical_accuracy: 0.6139

1074/未知 443秒 410毫秒/步 - loss: 0.9726 - sparse_categorical_accuracy: 0.6139

1075/未知 443秒 410毫秒/步 - loss: 0.9723 - sparse_categorical_accuracy: 0.6140

1076/未知 444秒 410毫秒/步 - loss: 0.9721 - sparse_categorical_accuracy: 0.6141

1077/未知 444秒 410毫秒/步 - loss: 0.9719 - sparse_categorical_accuracy: 0.6141

1078/未知 445秒 410毫秒/步 - loss: 0.9717 - sparse_categorical_accuracy: 0.6142

1079/未知 445秒 410毫秒/步 - loss: 0.9716 - sparse_categorical_accuracy: 0.6143

1080/未知 445秒 410毫秒/步 - loss: 0.9714 - sparse_categorical_accuracy: 0.6143

1081/未知 446秒 410毫秒/步 - loss: 0.9712 - sparse_categorical_accuracy: 0.6144

1082/未知 446秒 410毫秒/步 - loss: 0.9710 - sparse_categorical_accuracy: 0.6145

1083/未知 447秒 410毫秒/步 - loss: 0.9708 - sparse_categorical_accuracy: 0.6145

1084/未知 447秒 410毫秒/步 - loss: 0.9706 - sparse_categorical_accuracy: 0.6146

1085/未知 448秒 410毫秒/步 - loss: 0.9704 - sparse_categorical_accuracy: 0.6147

1086/未知 448秒 410毫秒/步 - loss: 0.9702 - sparse_categorical_accuracy: 0.6147

1087/未知 449秒 410毫秒/步 - loss: 0.9700 - sparse_categorical_accuracy: 0.6148

1088/未知 449秒 410毫秒/步 - loss: 0.9698 - sparse_categorical_accuracy: 0.6149

1089/未知 449秒 410毫秒/步 - loss: 0.9696 - sparse_categorical_accuracy: 0.6149

1090/未知 450秒 410毫秒/步 - loss: 0.9694 - sparse_categorical_accuracy: 0.6150

1091/未知 450秒 410毫秒/步 - loss: 0.9692 - sparse_categorical_accuracy: 0.6150

1092/未知 451秒 410毫秒/步 - loss: 0.9690 - sparse_categorical_accuracy: 0.6151

1093/未知 451秒 411毫秒/步 - loss: 0.9688 - sparse_categorical_accuracy: 0.6152

1094/未知 452秒 411毫秒/步 - loss: 0.9686 - sparse_categorical_accuracy: 0.6152

1095/未知 452秒 411毫秒/步 - loss: 0.9684 - sparse_categorical_accuracy: 0.6153

1096/未知 453秒 411毫秒/步 - loss: 0.9682 - sparse_categorical_accuracy: 0.6154

1097/未知 453秒 411毫秒/步 - loss: 0.9680 - sparse_categorical_accuracy: 0.6154

1098/未知 454秒 411毫秒/步 - loss: 0.9678 - sparse_categorical_accuracy: 0.6155

1099/未知 454秒 411毫秒/步 - loss: 0.9676 - sparse_categorical_accuracy: 0.6156

1100/未知 455秒 411毫秒/步 - loss: 0.9674 - sparse_categorical_accuracy: 0.6156

1101/未知 455秒 411毫秒/步 - loss: 0.9672 - sparse_categorical_accuracy: 0.6157

1102/未知 456秒 411毫秒/步 - loss: 0.9670 - sparse_categorical_accuracy: 0.6158

1103/未知 456秒 411毫秒/步 - loss: 0.9668 - sparse_categorical_accuracy: 0.6158

1104/未知 457秒 411毫秒/步 - loss: 0.9667 - sparse_categorical_accuracy: 0.6159

1105/未知 457秒 411毫秒/步 - loss: 0.9665 - sparse_categorical_accuracy: 0.6159

1106/未知 457秒 411毫秒/步 - loss: 0.9663 - sparse_categorical_accuracy: 0.6160

1107/未知 458秒 411毫秒/步 - loss: 0.9661 - sparse_categorical_accuracy: 0.6161

1108/未知 458秒 411毫秒/步 - loss: 0.9659 - sparse_categorical_accuracy: 0.6161

1109/未知 459秒 411毫秒/步 - loss: 0.9657 - sparse_categorical_accuracy: 0.6162

1110/未知 459秒 411毫秒/步 - loss: 0.9655 - sparse_categorical_accuracy: 0.6163

1111/未知 459秒 411毫秒/步 - loss: 0.9653 - sparse_categorical_accuracy: 0.6163

1112/未知 460秒 411毫秒/步 - loss: 0.9651 - sparse_categorical_accuracy: 0.6164

1113/未知 460秒 411毫秒/步 - loss: 0.9649 - sparse_categorical_accuracy: 0.6165

1114/未知 461秒 411毫秒/步 - loss: 0.9647 - sparse_categorical_accuracy: 0.6165

1115/未知 461秒 411毫秒/步 - loss: 0.9645 - sparse_categorical_accuracy: 0.6166

1116/未知 462秒 411毫秒/步 - loss: 0.9644 - sparse_categorical_accuracy: 0.6166

1117/未知 462秒 412毫秒/步 - loss: 0.9642 - sparse_categorical_accuracy: 0.6167

1118/未知 463秒 412毫秒/步 - loss: 0.9640 - sparse_categorical_accuracy: 0.6168

1119/未知 463秒 412毫秒/步 - loss: 0.9638 - sparse_categorical_accuracy: 0.6168

1120/未知 464秒 412毫秒/步 - loss: 0.9636 - sparse_categorical_accuracy: 0.6169

1121/未知 464秒 412毫秒/步 - loss: 0.9634 - sparse_categorical_accuracy: 0.6170

1122/未知 465秒 412毫秒/步 - loss: 0.9632 - sparse_categorical_accuracy: 0.6170

1123/未知 465秒 412毫秒/步 - loss: 0.9630 - sparse_categorical_accuracy: 0.6171

1124/未知 466秒 412毫秒/步 - loss: 0.9628 - sparse_categorical_accuracy: 0.6171

1125/未知 466秒 412毫秒/步 - loss: 0.9627 - sparse_categorical_accuracy: 0.6172

1126/未知 467秒 412毫秒/步 - loss: 0.9625 - sparse_categorical_accuracy: 0.6173

1127/未知 467秒 412毫秒/步 - loss: 0.9623 - sparse_categorical_accuracy: 0.6173

1128/未知 468秒 412毫秒/步 - loss: 0.9621 - sparse_categorical_accuracy: 0.6174

1129/未知 468秒 412毫秒/步 - loss: 0.9619 - sparse_categorical_accuracy: 0.6174

1130/未知 469秒 412毫秒/步 - loss: 0.9617 - sparse_categorical_accuracy: 0.6175

1131/未知 469秒 412毫秒/步 - loss: 0.9615 - sparse_categorical_accuracy: 0.6176

1132/未知 470秒 412毫秒/步 - loss: 0.9614 - sparse_categorical_accuracy: 0.6176

1133/未知 470秒 412毫秒/步 - loss: 0.9612 - sparse_categorical_accuracy: 0.6177

1134/未知 471秒 413毫秒/步 - loss: 0.9610 - sparse_categorical_accuracy: 0.6178

1135/未知 471秒 413毫秒/步 - loss: 0.9608 - sparse_categorical_accuracy: 0.6178

1136/未知 471秒 413毫秒/步 - loss: 0.9606 - sparse_categorical_accuracy: 0.6179

1137/未知 472秒 413毫秒/步 - loss: 0.9604 - sparse_categorical_accuracy: 0.6179

1138/未知 472秒 413毫秒/步 - loss: 0.9602 - sparse_categorical_accuracy: 0.6180

1139/未知 473秒 413毫秒/步 - loss: 0.9601 - sparse_categorical_accuracy: 0.6181

1140/未知 473秒 413毫秒/步 - loss: 0.9599 - sparse_categorical_accuracy: 0.6181

1141/未知 474秒 413毫秒/步 - loss: 0.9597 - sparse_categorical_accuracy: 0.6182

1142/未知 474秒 413毫秒/步 - loss: 0.9595 - sparse_categorical_accuracy: 0.6182

1143/未知 475秒 413毫秒/步 - loss: 0.9593 - sparse_categorical_accuracy: 0.6183

1144/未知 475秒 413毫秒/步 - loss: 0.9591 - sparse_categorical_accuracy: 0.6184

1145/未知 476秒 413毫秒/步 - loss: 0.9590 - sparse_categorical_accuracy: 0.6184

1146/未知 476秒 413毫秒/步 - loss: 0.9588 - sparse_categorical_accuracy: 0.6185

1147/未知 477秒 413毫秒/步 - loss: 0.9586 - sparse_categorical_accuracy: 0.6185

1148/未知 477秒 413毫秒/步 - loss: 0.9584 - sparse_categorical_accuracy: 0.6186

1149/未知 478秒 413毫秒/步 - loss: 0.9582 - sparse_categorical_accuracy: 0.6187

1150/未知 478秒 413毫秒/步 - loss: 0.9580 - sparse_categorical_accuracy: 0.6187

1151/未知 479秒 413毫秒/步 - loss: 0.9579 - sparse_categorical_accuracy: 0.6188

1152/未知 479秒 413毫秒/步 - loss: 0.9577 - sparse_categorical_accuracy: 0.6188

1153/未知 479秒 413毫秒/步 - loss: 0.9575 - sparse_categorical_accuracy: 0.6189

1154/未知 480秒 413毫秒/步 - loss: 0.9573 - sparse_categorical_accuracy: 0.6190

1155/未知 480秒 413毫秒/步 - loss: 0.9571 - sparse_categorical_accuracy: 0.6190

1156/未知 480秒 413毫秒/步 - loss: 0.9570 - sparse_categorical_accuracy: 0.6191

1157/未知 481秒 413毫秒/步 - loss: 0.9568 - sparse_categorical_accuracy: 0.6191

1158/未知 481秒 413毫秒/步 - loss: 0.9566 - sparse_categorical_accuracy: 0.6192

1159/未知 482秒 413毫秒/步 - loss: 0.9564 - sparse_categorical_accuracy: 0.6193

1160/未知 482秒 413毫秒/步 - loss: 0.9562 - sparse_categorical_accuracy: 0.6193

1161/未知 482秒 413毫秒/步 - loss: 0.9561 - sparse_categorical_accuracy: 0.6194

1162/未知 483秒 413毫秒/步 - loss: 0.9559 - sparse_categorical_accuracy: 0.6194

1163/未知 483秒 413毫秒/步 - loss: 0.9557 - sparse_categorical_accuracy: 0.6195

1164/未知 484秒 413毫秒/步 - loss: 0.9555 - sparse_categorical_accuracy: 0.6196

1165/未知 484秒 413毫秒/步 - loss: 0.9554 - sparse_categorical_accuracy: 0.6196

1166/未知 484秒 413毫秒/步 - loss: 0.9552 - sparse_categorical_accuracy: 0.6197

1167/未知 485秒 413毫秒/步 - loss: 0.9550 - sparse_categorical_accuracy: 0.6197

1168/未知 485秒 413毫秒/步 - loss: 0.9548 - sparse_categorical_accuracy: 0.6198

1169/未知 486秒 413毫秒/步 - loss: 0.9546 - sparse_categorical_accuracy: 0.6199

1170/未知 486秒 413毫秒/步 - loss: 0.9545 - sparse_categorical_accuracy: 0.6199

1171/未知 487秒 413毫秒/步 - loss: 0.9543 - sparse_categorical_accuracy: 0.6200

1172/未知 487秒 413毫秒/步 - loss: 0.9541 - sparse_categorical_accuracy: 0.6200

1173/未知 488秒 413毫秒/步 - loss: 0.9539 - sparse_categorical_accuracy: 0.6201

1174/未知 488秒 413毫秒/步 - loss: 0.9538 - sparse_categorical_accuracy: 0.6201

1175/未知 489秒 413毫秒/步 - loss: 0.9536 - sparse_categorical_accuracy: 0.6202

1176/未知 489秒 413毫秒/步 - loss: 0.9534 - sparse_categorical_accuracy: 0.6203

1177/未知 489秒 413毫秒/步 - loss: 0.9532 - sparse_categorical_accuracy: 0.6203

1178/未知 490秒 413毫秒/步 - loss: 0.9531 - sparse_categorical_accuracy: 0.6204

1179/未知 490秒 413毫秒/步 - loss: 0.9529 - sparse_categorical_accuracy: 0.6204

1180/未知 491秒 414毫秒/步 - loss: 0.9527 - sparse_categorical_accuracy: 0.6205

1181/未知 491秒 414毫秒/步 - loss: 0.9525 - sparse_categorical_accuracy: 0.6206

1182/未知 492秒 414毫秒/步 - loss: 0.9524 - sparse_categorical_accuracy: 0.6206

1183/未知 492秒 414毫秒/步 - loss: 0.9522 - sparse_categorical_accuracy: 0.6207

1184/未知 492秒 414毫秒/步 - loss: 0.9520 - sparse_categorical_accuracy: 0.6207

1185/未知 493秒 414毫秒/步 - loss: 0.9518 - sparse_categorical_accuracy: 0.6208

1186/未知 493秒 413毫秒/步 - loss: 0.9517 - sparse_categorical_accuracy: 0.6208

1187/未知 493秒 413毫秒/步 - loss: 0.9515 - sparse_categorical_accuracy: 0.6209

1188/未知 494秒 413毫秒/步 - loss: 0.9513 - sparse_categorical_accuracy: 0.6210

1189/未知 494秒 413毫秒/步 - loss: 0.9511 - sparse_categorical_accuracy: 0.6210

1190/未知 495秒 413毫秒/步 - loss: 0.9510 - sparse_categorical_accuracy: 0.6211

1191/未知 495秒 413毫秒/步 - loss: 0.9508 - sparse_categorical_accuracy: 0.6211

1192/未知 495秒 413毫秒/步 - loss: 0.9506 - sparse_categorical_accuracy: 0.6212

1193/未知 496秒 413毫秒/步 - loss: 0.9504 - sparse_categorical_accuracy: 0.6212

1194/未知 496秒 413毫秒/步 - loss: 0.9503 - sparse_categorical_accuracy: 0.6213

1195/未知 496秒 413毫秒/步 - loss: 0.9501 - sparse_categorical_accuracy: 0.6214

1196/未知 497秒 413毫秒/步 - loss: 0.9499 - sparse_categorical_accuracy: 0.6214

1197/未知 497秒 413毫秒/步 - loss: 0.9498 - sparse_categorical_accuracy: 0.6215

1198/未知 498秒 413毫秒/步 - loss: 0.9496 - sparse_categorical_accuracy: 0.6215

1199/未知 498秒 413毫秒/步 - loss: 0.9494 - sparse_categorical_accuracy: 0.6216

1200/未知 499秒 413毫秒/步 - loss: 0.9492 - sparse_categorical_accuracy: 0.6216

1201/未知 499秒 413毫秒/步 - loss: 0.9491 - sparse_categorical_accuracy: 0.6217

1202/未知 500秒 413毫秒/步 - loss: 0.9489 - sparse_categorical_accuracy: 0.6218

1203/未知 500秒 413毫秒/步 - loss: 0.9487 - sparse_categorical_accuracy: 0.6218

1204/未知 500秒 413毫秒/步 - loss: 0.9486 - sparse_categorical_accuracy: 0.6219

1205/未知 501秒 413毫秒/步 - loss: 0.9484 - sparse_categorical_accuracy: 0.6219

1206/未知 501秒 413毫秒/步 - loss: 0.9482 - sparse_categorical_accuracy: 0.6220

1207/未知 501秒 413毫秒/步 - loss: 0.9481 - sparse_categorical_accuracy: 0.6220

1208/未知 502秒 413毫秒/步 - loss: 0.9479 - sparse_categorical_accuracy: 0.6221

1209/未知 502秒 413毫秒/步 - loss: 0.9477 - sparse_categorical_accuracy: 0.6221

1210/未知 503秒 413毫秒/步 - loss: 0.9476 - sparse_categorical_accuracy: 0.6222

1211/未知 503秒 413毫秒/步 - loss: 0.9474 - sparse_categorical_accuracy: 0.6223

1212/未知 503秒 413毫秒/步 - loss: 0.9472 - sparse_categorical_accuracy: 0.6223

1213/未知 504秒 413毫秒/步 - loss: 0.9470 - sparse_categorical_accuracy: 0.6224

1214/未知 504秒 413毫秒/步 - loss: 0.9469 - sparse_categorical_accuracy: 0.6224

1215/未知 505秒 413毫秒/步 - loss: 0.9467 - sparse_categorical_accuracy: 0.6225

1216/未知 505秒 413毫秒/步 - loss: 0.9465 - sparse_categorical_accuracy: 0.6225

1217/未知 506秒 413毫秒/步 - loss: 0.9464 - sparse_categorical_accuracy: 0.6226

1218/未知 506秒 413毫秒/步 - loss: 0.9462 - sparse_categorical_accuracy: 0.6226

1219/未知 506秒 413毫秒/步 - loss: 0.9460 - sparse_categorical_accuracy: 0.6227

1220/未知 507秒 413毫秒/步 - loss: 0.9459 - sparse_categorical_accuracy: 0.6228

1221/未知 507秒 413毫秒/步 - loss: 0.9457 - sparse_categorical_accuracy: 0.6228

1222/未知 508秒 413毫秒/步 - loss: 0.9455 - sparse_categorical_accuracy: 0.6229

1223/未知 508秒 413毫秒/步 - loss: 0.9454 - sparse_categorical_accuracy: 0.6229

1224/未知 509秒 413毫秒/步 - loss: 0.9452 - sparse_categorical_accuracy: 0.6230

1225/未知 509秒 413毫秒/步 - loss: 0.9450 - sparse_categorical_accuracy: 0.6230

1226/未知 509秒 413毫秒/步 - loss: 0.9449 - sparse_categorical_accuracy: 0.6231

1227/未知 510秒 413毫秒/步 - loss: 0.9447 - sparse_categorical_accuracy: 0.6231

1228/未知 510秒 413毫秒/步 - loss: 0.9446 - sparse_categorical_accuracy: 0.6232

1229/未知 511秒 413毫秒/步 - loss: 0.9444 - sparse_categorical_accuracy: 0.6233

1230/未知 511秒 413毫秒/步 - loss: 0.9442 - sparse_categorical_accuracy: 0.6233

1231/未知 512秒 413毫秒/步 - loss: 0.9441 - sparse_categorical_accuracy: 0.6234

1232/未知 512秒 414毫秒/步 - loss: 0.9439 - sparse_categorical_accuracy: 0.6234

1233/未知 513秒 414毫秒/步 - loss: 0.9437 - sparse_categorical_accuracy: 0.6235

1234/未知 513秒 414毫秒/步 - loss: 0.9436 - sparse_categorical_accuracy: 0.6235

1235/未知 513秒 414毫秒/步 - loss: 0.9434 - sparse_categorical_accuracy: 0.6236

1236/未知 514秒 414毫秒/步 - loss: 0.9432 - sparse_categorical_accuracy: 0.6236

1237/未知 514秒 414毫秒/步 - loss: 0.9431 - sparse_categorical_accuracy: 0.6237

1238/未知 515秒 414毫秒/步 - loss: 0.9429 - sparse_categorical_accuracy: 0.6237

1239/未知 515秒 414毫秒/步 - loss: 0.9427 - sparse_categorical_accuracy: 0.6238

1240/未知 516秒 414毫秒/步 - loss: 0.9426 - sparse_categorical_accuracy: 0.6239

1241/未知 516秒 414毫秒/步 - loss: 0.9424 - sparse_categorical_accuracy: 0.6239

1242/未知 517秒 414毫秒/步 - loss: 0.9423 - sparse_categorical_accuracy: 0.6240

1243/未知 517秒 414毫秒/步 - loss: 0.9421 - sparse_categorical_accuracy: 0.6240

1244/未知 518秒 414毫秒/步 - loss: 0.9419 - sparse_categorical_accuracy: 0.6241

1245/未知 518秒 414毫秒/步 - loss: 0.9418 - sparse_categorical_accuracy: 0.6241

1246/未知 519秒 414毫秒/步 - loss: 0.9416 - sparse_categorical_accuracy: 0.6242

1247/未知 519秒 414毫秒/步 - loss: 0.9415 - sparse_categorical_accuracy: 0.6242

1248/未知 519秒 414毫秒/步 - loss: 0.9413 - sparse_categorical_accuracy: 0.6243

1249/未知 520秒 414毫秒/步 - loss: 0.9411 - sparse_categorical_accuracy: 0.6243

1250/未知 520秒 414毫秒/步 - loss: 0.9410 - sparse_categorical_accuracy: 0.6244

1251/未知 521秒 414毫秒/步 - loss: 0.9408 - sparse_categorical_accuracy: 0.6244

1252/未知 521秒 414毫秒/步 - loss: 0.9406 - sparse_categorical_accuracy: 0.6245

1253/未知 521秒 414毫秒/步 - loss: 0.9405 - sparse_categorical_accuracy: 0.6245

1254/未知 522秒 414毫秒/步 - loss: 0.9403 - sparse_categorical_accuracy: 0.6246

1255/未知 522秒 414毫秒/步 - loss: 0.9402 - sparse_categorical_accuracy: 0.6247

1256/未知 522秒 414毫秒/步 - loss: 0.9400 - sparse_categorical_accuracy: 0.6247

1257/未知 523秒 414毫秒/步 - loss: 0.9398 - sparse_categorical_accuracy: 0.6248

1258/未知 523秒 414毫秒/步 - loss: 0.9397 - sparse_categorical_accuracy: 0.6248

1259/未知 524秒 414毫秒/步 - loss: 0.9395 - sparse_categorical_accuracy: 0.6249

1260/未知 524秒 414毫秒/步 - loss: 0.9394 - sparse_categorical_accuracy: 0.6249

1261/未知 524秒 414毫秒/步 - loss: 0.9392 - sparse_categorical_accuracy: 0.6250

1262/未知 525秒 414毫秒/步 - loss: 0.9391 - sparse_categorical_accuracy: 0.6250

1263/未知 525秒 414毫秒/步 - loss: 0.9389 - sparse_categorical_accuracy: 0.6251

1264/未知 526秒 414毫秒/步 - loss: 0.9387 - sparse_categorical_accuracy: 0.6251

1265/未知 526秒 414毫秒/步 - loss: 0.9386 - sparse_categorical_accuracy: 0.6252

1266/未知 527秒 414毫秒/步 - loss: 0.9384 - sparse_categorical_accuracy: 0.6252

1267/未知 527秒 414毫秒/步 - loss: 0.9383 - sparse_categorical_accuracy: 0.6253

1268/未知 527秒 414毫秒/步 - loss: 0.9381 - sparse_categorical_accuracy: 0.6253

1269/未知 528秒 414毫秒/步 - loss: 0.9380 - sparse_categorical_accuracy: 0.6254

1270/未知 528秒 414毫秒/步 - loss: 0.9378 - sparse_categorical_accuracy: 0.6254

1271/未知 529秒 414毫秒/步 - loss: 0.9376 - sparse_categorical_accuracy: 0.6255

1272/未知 529秒 414毫秒/步 - loss: 0.9375 - sparse_categorical_accuracy: 0.6255

1273/未知 530秒 414毫秒/步 - loss: 0.9373 - sparse_categorical_accuracy: 0.6256

1274/未知 530秒 414毫秒/步 - loss: 0.9372 - sparse_categorical_accuracy: 0.6256

1275/未知 531秒 414毫秒/步 - loss: 0.9370 - sparse_categorical_accuracy: 0.6257

1276/未知 531秒 414毫秒/步 - loss: 0.9369 - sparse_categorical_accuracy: 0.6257

1277/未知 532秒 414毫秒/步 - loss: 0.9367 - sparse_categorical_accuracy: 0.6258

1278/未知 532秒 414毫秒/步 - loss: 0.9365 - sparse_categorical_accuracy: 0.6259

1279/未知 532秒 414毫秒/步 - loss: 0.9364 - sparse_categorical_accuracy: 0.6259

1280/未知 533秒 414毫秒/步 - loss: 0.9362 - sparse_categorical_accuracy: 0.6260

1281/未知 533秒 414毫秒/步 - loss: 0.9361 - sparse_categorical_accuracy: 0.6260

1282/未知 534秒 414毫秒/步 - loss: 0.9359 - sparse_categorical_accuracy: 0.6261

1283/未知 534秒 414毫秒/步 - loss: 0.9358 - sparse_categorical_accuracy: 0.6261

1284/未知 535秒 414毫秒/步 - loss: 0.9356 - sparse_categorical_accuracy: 0.6262

1285/未知 535秒 414毫秒/步 - loss: 0.9355 - sparse_categorical_accuracy: 0.6262

1286/未知 535秒 414毫秒/步 - loss: 0.9353 - sparse_categorical_accuracy: 0.6263

1287/未知 536秒 414毫秒/步 - loss: 0.9352 - sparse_categorical_accuracy: 0.6263

1288/未知 536秒 414毫秒/步 - loss: 0.9350 - sparse_categorical_accuracy: 0.6264

1289/未知 537秒 414毫秒/步 - loss: 0.9348 - sparse_categorical_accuracy: 0.6264

1290/未知 537秒 414毫秒/步 - loss: 0.9347 - sparse_categorical_accuracy: 0.6265

1291/未知 537秒 414毫秒/步 - loss: 0.9345 - sparse_categorical_accuracy: 0.6265

1292/未知 538秒 414毫秒/步 - loss: 0.9344 - sparse_categorical_accuracy: 0.6266

1293/未知 538秒 414毫秒/步 - loss: 0.9342 - sparse_categorical_accuracy: 0.6266

1294/未知 539秒 414毫秒/步 - loss: 0.9341 - sparse_categorical_accuracy: 0.6267

1295/未知 539秒 414毫秒/步 - loss: 0.9339 - sparse_categorical_accuracy: 0.6267

1296/未知 539秒 414毫秒/步 - loss: 0.9338 - sparse_categorical_accuracy: 0.6268

1297/未知 540秒 414毫秒/步 - loss: 0.9336 - sparse_categorical_accuracy: 0.6268

1298/未知 540秒 414毫秒/步 - loss: 0.9335 - sparse_categorical_accuracy: 0.6269

1299/未知 540秒 414毫秒/步 - loss: 0.9333 - sparse_categorical_accuracy: 0.6269

1300/未知 541秒 414毫秒/步 - loss: 0.9332 - sparse_categorical_accuracy: 0.6270

1301/未知 541秒 414毫秒/步 - loss: 0.9330 - sparse_categorical_accuracy: 0.6270

1302/未知 542秒 414毫秒/步 - loss: 0.9329 - sparse_categorical_accuracy: 0.6271

1303/未知 542秒 414毫秒/步 - loss: 0.9327 - sparse_categorical_accuracy: 0.6271

1304/未知 542秒 414毫秒/步 - loss: 0.9326 - sparse_categorical_accuracy: 0.6272

1305/未知 543秒 414毫秒/步 - loss: 0.9324 - sparse_categorical_accuracy: 0.6272

1306/未知 543秒 414毫秒/步 - loss: 0.9323 - sparse_categorical_accuracy: 0.6273

1307/未知 544秒 414毫秒/步 - loss: 0.9321 - sparse_categorical_accuracy: 0.6273

1308/未知 544秒 414毫秒/步 - loss: 0.9320 - sparse_categorical_accuracy: 0.6274

1309/未知 544秒 414毫秒/步 - loss: 0.9318 - sparse_categorical_accuracy: 0.6274

1310/未知 545秒 414毫秒/步 - loss: 0.9317 - sparse_categorical_accuracy: 0.6275

1311/未知 545秒 414毫秒/步 - loss: 0.9315 - sparse_categorical_accuracy: 0.6275

1312/未知 546秒 414毫秒/步 - loss: 0.9314 - sparse_categorical_accuracy: 0.6276

1313/未知 546秒 414毫秒/步 - loss: 0.9312 - sparse_categorical_accuracy: 0.6276

1314/未知 547秒 414毫秒/步 - loss: 0.9311 - sparse_categorical_accuracy: 0.6277

1315/未知 547秒 414毫秒/步 - loss: 0.9309 - sparse_categorical_accuracy: 0.6277

1316/未知 548秒 414毫秒/步 - loss: 0.9308 - sparse_categorical_accuracy: 0.6278

1317/未知 548秒 414毫秒/步 - loss: 0.9306 - sparse_categorical_accuracy: 0.6278

1318/未知 549秒 414毫秒/步 - loss: 0.9305 - sparse_categorical_accuracy: 0.6279

1319/未知 549秒 414毫秒/步 - loss: 0.9303 - sparse_categorical_accuracy: 0.6279

1320/未知 550秒 414毫秒/步 - loss: 0.9302 - sparse_categorical_accuracy: 0.6280

1321/未知 550秒 414毫秒/步 - loss: 0.9300 - sparse_categorical_accuracy: 0.6280

1322/未知 551秒 414毫秒/步 - loss: 0.9299 - sparse_categorical_accuracy: 0.6281

1323/未知 551秒 415毫秒/步 - loss: 0.9297 - sparse_categorical_accuracy: 0.6281

1324/未知 552秒 415毫秒/步 - loss: 0.9296 - sparse_categorical_accuracy: 0.6282

1325/未知 552秒 415毫秒/步 - loss: 0.9294 - sparse_categorical_accuracy: 0.6282

1326/未知 553秒 415毫秒/步 - loss: 0.9293 - sparse_categorical_accuracy: 0.6283

1327/未知 553秒 415毫秒/步 - loss: 0.9291 - sparse_categorical_accuracy: 0.6283

1328/未知 553秒 415毫秒/步 - loss: 0.9290 - sparse_categorical_accuracy: 0.6284

1329/未知 554秒 415毫秒/步 - loss: 0.9288 - sparse_categorical_accuracy: 0.6284

1330/未知 554秒 415毫秒/步 - loss: 0.9287 - sparse_categorical_accuracy: 0.6285

1331/未知 555秒 415毫秒/步 - loss: 0.9285 - sparse_categorical_accuracy: 0.6285

1332/未知 555秒 415毫秒/步 - loss: 0.9284 - sparse_categorical_accuracy: 0.6285

1333/未知 556秒 415毫秒/步 - loss: 0.9283 - sparse_categorical_accuracy: 0.6286

1334/未知 556秒 415毫秒/步 - loss: 0.9281 - sparse_categorical_accuracy: 0.6286

1335/未知 556秒 415毫秒/步 - loss: 0.9280 - sparse_categorical_accuracy: 0.6287

1336/未知 557秒 415毫秒/步 - loss: 0.9278 - sparse_categorical_accuracy: 0.6287

1337/未知 557秒 415毫秒/步 - loss: 0.9277 - sparse_categorical_accuracy: 0.6288

1338/未知 558秒 415毫秒/步 - loss: 0.9275 - sparse_categorical_accuracy: 0.6288

1339/未知 558秒 415毫秒/步 - loss: 0.9274 - sparse_categorical_accuracy: 0.6289

1340/未知 559秒 415毫秒/步 - loss: 0.9272 - sparse_categorical_accuracy: 0.6289

1341/未知 559秒 415毫秒/步 - loss: 0.9271 - sparse_categorical_accuracy: 0.6290

1342/未知 560秒 415毫秒/步 - loss: 0.9269 - sparse_categorical_accuracy: 0.6290

1343/未知 560秒 415毫秒/步 - loss: 0.9268 - sparse_categorical_accuracy: 0.6291

1344/未知 561秒 415毫秒/步 - loss: 0.9267 - sparse_categorical_accuracy: 0.6291

1345/未知 561秒 415毫秒/步 - loss: 0.9265 - sparse_categorical_accuracy: 0.6292

1346/未知 561秒 415毫秒/步 - loss: 0.9264 - sparse_categorical_accuracy: 0.6292

1347/未知 562秒 415毫秒/步 - loss: 0.9262 - sparse_categorical_accuracy: 0.6293

1348/未知 562秒 415毫秒/步 - loss: 0.9261 - sparse_categorical_accuracy: 0.6293

1349/未知 563秒 415毫秒/步 - loss: 0.9259 - sparse_categorical_accuracy: 0.6294

1350/未知 563秒 415毫秒/步 - loss: 0.9258 - sparse_categorical_accuracy: 0.6294

1351/未知 564秒 415毫秒/步 - loss: 0.9256 - sparse_categorical_accuracy: 0.6295

1352/未知 564秒 415毫秒/步 - loss: 0.9255 - sparse_categorical_accuracy: 0.6295

1353/未知 564秒 415毫秒/步 - loss: 0.9254 - sparse_categorical_accuracy: 0.6296

1354/未知 565秒 415毫秒/步 - loss: 0.9252 - sparse_categorical_accuracy: 0.6296

1355/未知 565秒 415毫秒/步 - loss: 0.9251 - sparse_categorical_accuracy: 0.6296

1356/未知 565秒 415毫秒/步 - loss: 0.9249 - sparse_categorical_accuracy: 0.6297

1357/未知 566秒 415毫秒/步 - loss: 0.9248 - sparse_categorical_accuracy: 0.6297

1358/未知 566秒 415毫秒/步 - loss: 0.9246 - sparse_categorical_accuracy: 0.6298

1359/未知 566秒 415毫秒/步 - loss: 0.9245 - sparse_categorical_accuracy: 0.6298

1360/未知 567秒 415毫秒/步 - loss: 0.9244 - sparse_categorical_accuracy: 0.6299

1361/未知 567秒 415毫秒/步 - loss: 0.9242 - sparse_categorical_accuracy: 0.6299

1362/未知 568秒 415毫秒/步 - loss: 0.9241 - sparse_categorical_accuracy: 0.6300

1363/未知 568秒 415毫秒/步 - loss: 0.9239 - sparse_categorical_accuracy: 0.6300

1364/未知 568秒 415毫秒/步 - loss: 0.9238 - sparse_categorical_accuracy: 0.6301

1365/未知 569秒 415毫秒/步 - loss: 0.9237 - sparse_categorical_accuracy: 0.6301

1366/未知 569秒 415毫秒/步 - loss: 0.9235 - sparse_categorical_accuracy: 0.6302

1367/未知 570秒 415毫秒/步 - loss: 0.9234 - sparse_categorical_accuracy: 0.6302

1368/未知 570秒 415毫秒/步 - loss: 0.9232 - sparse_categorical_accuracy: 0.6303

1369/未知 571秒 415毫秒/步 - loss: 0.9231 - sparse_categorical_accuracy: 0.6303

1370/未知 571秒 415毫秒/步 - loss: 0.9229 - sparse_categorical_accuracy: 0.6304

1371/未知 572秒 415毫秒/步 - loss: 0.9228 - sparse_categorical_accuracy: 0.6304

1372/未知 572秒 415毫秒/步 - loss: 0.9227 - sparse_categorical_accuracy: 0.6304

1373/未知 573秒 415毫秒/步 - loss: 0.9225 - sparse_categorical_accuracy: 0.6305

1374/未知 573秒 415毫秒/步 - loss: 0.9224 - sparse_categorical_accuracy: 0.6305

1375/未知 574秒 415毫秒/步 - loss: 0.9222 - sparse_categorical_accuracy: 0.6306

1376/未知 574秒 415毫秒/步 - loss: 0.9221 - sparse_categorical_accuracy: 0.6306

1377/未知 574秒 415毫秒/步 - loss: 0.9220 - sparse_categorical_accuracy: 0.6307

1378/未知 575秒 415毫秒/步 - loss: 0.9218 - sparse_categorical_accuracy: 0.6307

1379/未知 575秒 415毫秒/步 - loss: 0.9217 - sparse_categorical_accuracy: 0.6308

1380/未知 575秒 415毫秒/步 - loss: 0.9215 - sparse_categorical_accuracy: 0.6308

1381/未知 576秒 415毫秒/步 - loss: 0.9214 - sparse_categorical_accuracy: 0.6309

1382/未知 576秒 415毫秒/步 - loss: 0.9213 - sparse_categorical_accuracy: 0.6309

1383/未知 576秒 415毫秒/步 - loss: 0.9211 - sparse_categorical_accuracy: 0.6309

1384/未知 577秒 415毫秒/步 - loss: 0.9210 - sparse_categorical_accuracy: 0.6310

1385/未知 577秒 415毫秒/步 - loss: 0.9209 - sparse_categorical_accuracy: 0.6310

1386/未知 578秒 415毫秒/步 - loss: 0.9207 - sparse_categorical_accuracy: 0.6311

1387/未知 578秒 415毫秒/步 - loss: 0.9206 - sparse_categorical_accuracy: 0.6311

1388/未知 578秒 415毫秒/步 - loss: 0.9204 - sparse_categorical_accuracy: 0.6312

1389/未知 579秒 415毫秒/步 - loss: 0.9203 - sparse_categorical_accuracy: 0.6312

1390/未知 579秒 415毫秒/步 - loss: 0.9202 - sparse_categorical_accuracy: 0.6313

1391/未知 580秒 415毫秒/步 - loss: 0.9200 - sparse_categorical_accuracy: 0.6313

1392/未知 580秒 415毫秒/步 - loss: 0.9199 - sparse_categorical_accuracy: 0.6314

1393/未知 580秒 415毫秒/步 - loss: 0.9198 - sparse_categorical_accuracy: 0.6314

1394/未知 581秒 415毫秒/步 - loss: 0.9196 - sparse_categorical_accuracy: 0.6315

1395/未知 581秒 415毫秒/步 - loss: 0.9195 - sparse_categorical_accuracy: 0.6315

1396/未知 582秒 415毫秒/步 - loss: 0.9193 - sparse_categorical_accuracy: 0.6315

1397/未知 582秒 415毫秒/步 - loss: 0.9192 - sparse_categorical_accuracy: 0.6316

1398/未知 583秒 415毫秒/步 - loss: 0.9191 - sparse_categorical_accuracy: 0.6316

1399/未知 583秒 415毫秒/步 - loss: 0.9189 - sparse_categorical_accuracy: 0.6317

1400/未知 583秒 415毫秒/步 - loss: 0.9188 - sparse_categorical_accuracy: 0.6317

1401/未知 584秒 415毫秒/步 - loss: 0.9187 - sparse_categorical_accuracy: 0.6318

1402/未知 584秒 415毫秒/步 - loss: 0.9185 - sparse_categorical_accuracy: 0.6318

1403/未知 585秒 415毫秒/步 - loss: 0.9184 - sparse_categorical_accuracy: 0.6319

1404/未知 585秒 415毫秒/步 - loss: 0.9183 - sparse_categorical_accuracy: 0.6319

1405/未知 586秒 415毫秒/步 - loss: 0.9181 - sparse_categorical_accuracy: 0.6319

1406/未知 586秒 415毫秒/步 - loss: 0.9180 - sparse_categorical_accuracy: 0.6320

1407/未知 587秒 415毫秒/步 - loss: 0.9178 - sparse_categorical_accuracy: 0.6320

1408/未知 587秒 415毫秒/步 - loss: 0.9177 - sparse_categorical_accuracy: 0.6321

1409/未知 588秒 415毫秒/步 - loss: 0.9176 - sparse_categorical_accuracy: 0.6321

1410/未知 588秒 415毫秒/步 - loss: 0.9174 - sparse_categorical_accuracy: 0.6322

1411/未知 589秒 415毫秒/步 - loss: 0.9173 - sparse_categorical_accuracy: 0.6322

1412/未知 589秒 415毫秒/步 - loss: 0.9172 - sparse_categorical_accuracy: 0.6323

1413/未知 590秒 415毫秒/步 - loss: 0.9170 - sparse_categorical_accuracy: 0.6323

1414/未知 590秒 415毫秒/步 - loss: 0.9169 - sparse_categorical_accuracy: 0.6323

1415/未知 591秒 415毫秒/步 - loss: 0.9168 - sparse_categorical_accuracy: 0.6324

1416/未知 591秒 415毫秒/步 - loss: 0.9166 - sparse_categorical_accuracy: 0.6324

1417/未知 591秒 415毫秒/步 - loss: 0.9165 - sparse_categorical_accuracy: 0.6325

1418/未知 592秒 415毫秒/步 - loss: 0.9164 - sparse_categorical_accuracy: 0.6325

1419/未知 592秒 415毫秒/步 - loss: 0.9162 - sparse_categorical_accuracy: 0.6326

1420/未知 592秒 415毫秒/步 - loss: 0.9161 - sparse_categorical_accuracy: 0.6326

1421/未知 593秒 415毫秒/步 - loss: 0.9160 - sparse_categorical_accuracy: 0.6327

1422/未知 593秒 415毫秒/步 - loss: 0.9158 - sparse_categorical_accuracy: 0.6327

1423/未知 594秒 415毫秒/步 - loss: 0.9157 - sparse_categorical_accuracy: 0.6327

1424/未知 594秒 415毫秒/步 - loss: 0.9156 - sparse_categorical_accuracy: 0.6328

1425/未知 594秒 415毫秒/步 - loss: 0.9154 - sparse_categorical_accuracy: 0.6328

1426/未知 595秒 415毫秒/步 - loss: 0.9153 - sparse_categorical_accuracy: 0.6329

1427/未知 595秒 415毫秒/步 - loss: 0.9152 - sparse_categorical_accuracy: 0.6329

1428/未知 596秒 415毫秒/步 - loss: 0.9150 - sparse_categorical_accuracy: 0.6330

1429/未知 596秒 415毫秒/步 - loss: 0.9149 - sparse_categorical_accuracy: 0.6330

1430/未知 596秒 415毫秒/步 - loss: 0.9148 - sparse_categorical_accuracy: 0.6331

1431/未知 597秒 415毫秒/步 - loss: 0.9146 - sparse_categorical_accuracy: 0.6331

1432/未知 597秒 415毫秒/步 - loss: 0.9145 - sparse_categorical_accuracy: 0.6331

1433/未知 598秒 415毫秒/步 - loss: 0.9144 - sparse_categorical_accuracy: 0.6332

1434/未知 598秒 415毫秒/步 - loss: 0.9142 - sparse_categorical_accuracy: 0.6332

1435/未知 599秒 415毫秒/步 - loss: 0.9141 - sparse_categorical_accuracy: 0.6333

1436/未知 599秒 415毫秒/步 - loss: 0.9140 - sparse_categorical_accuracy: 0.6333

1437/未知 599秒 415毫秒/步 - loss: 0.9139 - sparse_categorical_accuracy: 0.6334

1438/未知 600秒 415毫秒/步 - loss: 0.9137 - sparse_categorical_accuracy: 0.6334

1439/未知 600秒 415毫秒/步 - loss: 0.9136 - sparse_categorical_accuracy: 0.6334

1440/未知 601秒 415毫秒/步 - loss: 0.9135 - sparse_categorical_accuracy: 0.6335

1441/未知 601秒 415毫秒/步 - loss: 0.9133 - sparse_categorical_accuracy: 0.6335

1442/未知 602秒 416毫秒/步 - loss: 0.9132 - sparse_categorical_accuracy: 0.6336

1443/未知 602秒 416毫秒/步 - loss: 0.9131 - sparse_categorical_accuracy: 0.6336

1444/未知 603秒 416毫秒/步 - loss: 0.9129 - sparse_categorical_accuracy: 0.6337

1445/未知 603秒 416毫秒/步 - loss: 0.9128 - sparse_categorical_accuracy: 0.6337

1446/未知 604秒 416毫秒/步 - loss: 0.9127 - sparse_categorical_accuracy: 0.6337

1447/未知 604秒 416毫秒/步 - loss: 0.9126 - sparse_categorical_accuracy: 0.6338

1448/未知 605秒 416毫秒/步 - loss: 0.9124 - sparse_categorical_accuracy: 0.6338

1449/未知 605秒 416毫秒/步 - loss: 0.9123 - sparse_categorical_accuracy: 0.6339

1450/未知 606秒 416毫秒/步 - loss: 0.9122 - sparse_categorical_accuracy: 0.6339

1451/未知 606秒 416毫秒/步 - loss: 0.9120 - sparse_categorical_accuracy: 0.6340

1452/未知 606秒 416毫秒/步 - loss: 0.9119 - sparse_categorical_accuracy: 0.6340

1453/未知 607秒 416毫秒/步 - loss: 0.9118 - sparse_categorical_accuracy: 0.6340

1454/未知 607秒 416毫秒/步 - loss: 0.9116 - sparse_categorical_accuracy: 0.6341

1455/未知 608秒 416毫秒/步 - loss: 0.9115 - sparse_categorical_accuracy: 0.6341

1456/未知 608秒 416毫秒/步 - loss: 0.9114 - sparse_categorical_accuracy: 0.6342

1457/未知 609秒 416毫秒/步 - loss: 0.9113 - sparse_categorical_accuracy: 0.6342

1458/未知 609秒 416毫秒/步 - loss: 0.9111 - sparse_categorical_accuracy: 0.6343

1459/未知 610秒 416毫秒/步 - loss: 0.9110 - sparse_categorical_accuracy: 0.6343

1460/未知 610秒 416毫秒/步 - loss: 0.9109 - sparse_categorical_accuracy: 0.6343

1461/未知 610秒 416毫秒/步 - loss: 0.9108 - sparse_categorical_accuracy: 0.6344

1462/未知 611秒 416毫秒/步 - loss: 0.9106 - sparse_categorical_accuracy: 0.6344

1463/未知 611秒 416毫秒/步 - loss: 0.9105 - sparse_categorical_accuracy: 0.6345

1464/未知 612秒 416毫秒/步 - loss: 0.9104 - sparse_categorical_accuracy: 0.6345

1465/未知 612秒 416毫秒/步 - loss: 0.9102 - sparse_categorical_accuracy: 0.6345

1466/未知 613秒 416毫秒/步 - loss: 0.9101 - sparse_categorical_accuracy: 0.6346

1467/未知 613秒 416毫秒/步 - loss: 0.9100 - sparse_categorical_accuracy: 0.6346

1468/未知 613秒 416毫秒/步 - loss: 0.9099 - sparse_categorical_accuracy: 0.6347

1469/未知 614秒 416毫秒/步 - loss: 0.9097 - sparse_categorical_accuracy: 0.6347

1470/未知 614秒 416毫秒/步 - loss: 0.9096 - sparse_categorical_accuracy: 0.6348

1471/未知 614秒 416毫秒/步 - loss: 0.9095 - sparse_categorical_accuracy: 0.6348

1472/未知 615秒 416毫秒/步 - loss: 0.9094 - sparse_categorical_accuracy: 0.6348

1473/未知 615秒 416毫秒/步 - loss: 0.9092 - sparse_categorical_accuracy: 0.6349

1474/未知 615秒 416毫秒/步 - loss: 0.9091 - sparse_categorical_accuracy: 0.6349

1475/未知 616秒 416毫秒/步 - loss: 0.9090 - sparse_categorical_accuracy: 0.6350

1476/未知 616秒 416毫秒/步 - loss: 0.9089 - sparse_categorical_accuracy: 0.6350

1477/未知 616秒 416毫秒/步 - loss: 0.9087 - sparse_categorical_accuracy: 0.6350

1478/未知 617秒 415毫秒/步 - loss: 0.9086 - sparse_categorical_accuracy: 0.6351

1479/未知 617秒 415毫秒/步 - loss: 0.9085 - sparse_categorical_accuracy: 0.6351

1480/未知 617秒 415毫秒/步 - loss: 0.9083 - sparse_categorical_accuracy: 0.6352

1481/未知 618秒 415毫秒/步 - loss: 0.9082 - sparse_categorical_accuracy: 0.6352

1482/未知 618秒 415毫秒/步 - loss: 0.9081 - sparse_categorical_accuracy: 0.6353

1483/未知 619秒 415毫秒/步 - loss: 0.9080 - sparse_categorical_accuracy: 0.6353

1484/未知 619秒 415毫秒/步 - loss: 0.9078 - sparse_categorical_accuracy: 0.6353

1485/未知 620秒 415毫秒/步 - loss: 0.9077 - sparse_categorical_accuracy: 0.6354

1486/未知 620秒 415毫秒/步 - loss: 0.9076 - sparse_categorical_accuracy: 0.6354

1487/未知 620秒 415毫秒/步 - loss: 0.9075 - sparse_categorical_accuracy: 0.6355

1488/未知 621秒 416毫秒/步 - loss: 0.9073 - sparse_categorical_accuracy: 0.6355

1489/未知 621秒 416毫秒/步 - loss: 0.9072 - sparse_categorical_accuracy: 0.6355

1490/未知 622秒 416毫秒/步 - loss: 0.9071 - sparse_categorical_accuracy: 0.6356

1491/未知 622秒 416毫秒/步 - loss: 0.9070 - sparse_categorical_accuracy: 0.6356

1492/未知 623秒 416毫秒/步 - loss: 0.9069 - sparse_categorical_accuracy: 0.6357

1493/未知 623秒 416毫秒/步 - loss: 0.9067 - sparse_categorical_accuracy: 0.6357

1494/未知 624秒 416毫秒/步 - loss: 0.9066 - sparse_categorical_accuracy: 0.6358

1495/未知 624秒 416毫秒/步 - loss: 0.9065 - sparse_categorical_accuracy: 0.6358

1496/未知 624秒 416毫秒/步 - loss: 0.9064 - sparse_categorical_accuracy: 0.6358

1497/未知 625秒 416毫秒/步 - loss: 0.9062 - sparse_categorical_accuracy: 0.6359

1498/未知 625秒 416毫秒/步 - loss: 0.9061 - sparse_categorical_accuracy: 0.6359

1499/未知 626秒 416毫秒/步 - loss: 0.9060 - sparse_categorical_accuracy: 0.6360

1500/未知 626秒 416毫秒/步 - loss: 0.9059 - sparse_categorical_accuracy: 0.6360

1501/未知 627秒 416毫秒/步 - loss: 0.9057 - sparse_categorical_accuracy: 0.6360

1502/未知 627秒 416毫秒/步 - loss: 0.9056 - sparse_categorical_accuracy: 0.6361

1503/未知 628秒 416毫秒/步 - loss: 0.9055 - sparse_categorical_accuracy: 0.6361

1504/未知 628秒 416毫秒/步 - loss: 0.9054 - sparse_categorical_accuracy: 0.6362

1505/未知 628秒 416毫秒/步 - loss: 0.9053 - sparse_categorical_accuracy: 0.6362

1506/未知 629秒 416毫秒/步 - loss: 0.9051 - sparse_categorical_accuracy: 0.6362

1507/未知 629秒 416毫秒/步 - loss: 0.9050 - sparse_categorical_accuracy: 0.6363

1508/未知 630秒 416毫秒/步 - loss: 0.9049 - sparse_categorical_accuracy: 0.6363

1509/未知 630秒 416毫秒/步 - loss: 0.9048 - sparse_categorical_accuracy: 0.6364

1510/未知 631秒 416毫秒/步 - loss: 0.9046 - sparse_categorical_accuracy: 0.6364

1511/未知 631秒 416毫秒/步 - loss: 0.9045 - sparse_categorical_accuracy: 0.6364

1512/未知 631秒 416毫秒/步 - loss: 0.9044 - sparse_categorical_accuracy: 0.6365

1513/未知 632秒 416毫秒/步 - loss: 0.9043 - sparse_categorical_accuracy: 0.6365

1514/未知 632秒 416毫秒/步 - loss: 0.9042 - sparse_categorical_accuracy: 0.6366

1515/未知 632秒 415毫秒/步 - loss: 0.9040 - sparse_categorical_accuracy: 0.6366

1516/未知 633秒 415毫秒/步 - loss: 0.9039 - sparse_categorical_accuracy: 0.6366

1517/未知 633秒 415毫秒/步 - loss: 0.9038 - sparse_categorical_accuracy: 0.6367

1518/未知 634秒 416毫秒/步 - loss: 0.9037 - sparse_categorical_accuracy: 0.6367

1519/未知 634秒 416毫秒/步 - loss: 0.9036 - sparse_categorical_accuracy: 0.6368

1520/未知 634秒 415毫秒/步 - loss: 0.9034 - sparse_categorical_accuracy: 0.6368

1521/未知 635秒 415毫秒/步 - loss: 0.9033 - sparse_categorical_accuracy: 0.6368

1522/未知 635秒 415毫秒/步 - loss: 0.9032 - sparse_categorical_accuracy: 0.6369

1523/未知 635秒 415毫秒/步 - loss: 0.9031 - sparse_categorical_accuracy: 0.6369

1524/未知 636秒 415毫秒/步 - loss: 0.9029 - sparse_categorical_accuracy: 0.6370

1525/未知 636秒 415毫秒/步 - loss: 0.9028 - sparse_categorical_accuracy: 0.6370

1526/未知 637秒 415毫秒/步 - loss: 0.9027 - sparse_categorical_accuracy: 0.6370

1527/未知 637秒 415毫秒/步 - loss: 0.9026 - sparse_categorical_accuracy: 0.6371

1528/未知 638秒 416毫秒/步 - loss: 0.9025 - sparse_categorical_accuracy: 0.6371

1529/未知 638秒 416毫秒/步 - loss: 0.9023 - sparse_categorical_accuracy: 0.6372

1530/未知 639秒 416毫秒/步 - loss: 0.9022 - sparse_categorical_accuracy: 0.6372

1531/未知 639秒 416毫秒/步 - loss: 0.9021 - sparse_categorical_accuracy: 0.6372

1532/未知 640秒 416毫秒/步 - loss: 0.9020 - sparse_categorical_accuracy: 0.6373

1533/未知 640秒 416毫秒/步 - loss: 0.9019 - sparse_categorical_accuracy: 0.6373

1534/未知 641秒 416毫秒/步 - loss: 0.9018 - sparse_categorical_accuracy: 0.6374

1535/未知 641秒 416毫秒/步 - loss: 0.9016 - sparse_categorical_accuracy: 0.6374

1536/未知 641秒 416毫秒/步 - loss: 0.9015 - sparse_categorical_accuracy: 0.6374

1537/未知 642秒 416毫秒/步 - loss: 0.9014 - sparse_categorical_accuracy: 0.6375

1538/未知 642秒 416毫秒/步 - loss: 0.9013 - sparse_categorical_accuracy: 0.6375

1539/未知 643秒 416毫秒/步 - loss: 0.9012 - sparse_categorical_accuracy: 0.6376

1540/未知 643秒 416毫秒/步 - loss: 0.9010 - sparse_categorical_accuracy: 0.6376

1541/未知 644秒 416毫秒/步 - loss: 0.9009 - sparse_categorical_accuracy: 0.6376

1542/未知 644秒 416毫秒/步 - loss: 0.9008 - sparse_categorical_accuracy: 0.6377

1543/未知 645秒 416毫秒/步 - loss: 0.9007 - sparse_categorical_accuracy: 0.6377

1544/未知 645秒 416毫秒/步 - loss: 0.9006 - sparse_categorical_accuracy: 0.6378

1545/未知 645秒 416毫秒/步 - loss: 0.9004 - sparse_categorical_accuracy: 0.6378

1546/未知 646秒 416毫秒/步 - loss: 0.9003 - sparse_categorical_accuracy: 0.6378

1547/未知 646秒 416毫秒/步 - loss: 0.9002 - sparse_categorical_accuracy: 0.6379

1548/未知 646秒 416毫秒/步 - loss: 0.9001 - sparse_categorical_accuracy: 0.6379

1549/未知 647秒 416毫秒/步 - loss: 0.9000 - sparse_categorical_accuracy: 0.6379

1550/未知 647秒 416毫秒/步 - loss: 0.8999 - sparse_categorical_accuracy: 0.6380

1551/未知 648秒 416毫秒/步 - loss: 0.8997 - sparse_categorical_accuracy: 0.6380

1552/未知 648秒 416毫秒/步 - loss: 0.8996 - sparse_categorical_accuracy: 0.6381

1553/未知 648秒 416毫秒/步 - loss: 0.8995 - sparse_categorical_accuracy: 0.6381

1554/未知 649秒 416毫秒/步 - loss: 0.8994 - sparse_categorical_accuracy: 0.6381

1555/未知 649秒 416毫秒/步 - loss: 0.8993 - sparse_categorical_accuracy: 0.6382

1556/未知 650秒 416毫秒/步 - loss: 0.8992 - sparse_categorical_accuracy: 0.6382

1557/未知 650秒 416毫秒/步 - loss: 0.8990 - sparse_categorical_accuracy: 0.6383

1558/未知 650秒 416毫秒/步 - loss: 0.8989 - sparse_categorical_accuracy: 0.6383

1559/未知 651秒 416毫秒/步 - loss: 0.8988 - sparse_categorical_accuracy: 0.6383

1560/未知 651秒 416毫秒/步 - loss: 0.8987 - sparse_categorical_accuracy: 0.6384

1561/未知 652秒 416毫秒/步 - loss: 0.8986 - sparse_categorical_accuracy: 0.6384

1562/未知 652秒 416毫秒/步 - loss: 0.8985 - sparse_categorical_accuracy: 0.6385

1563/未知 653秒 416毫秒/步 - loss: 0.8983 - sparse_categorical_accuracy: 0.6385

1564/未知 653秒 416毫秒/步 - loss: 0.8982 - sparse_categorical_accuracy: 0.6385

1565/未知 654秒 416毫秒/步 - loss: 0.8981 - sparse_categorical_accuracy: 0.6386

1566/未知 654秒 416毫秒/步 - loss: 0.8980 - sparse_categorical_accuracy: 0.6386

1567/未知 655秒 416毫秒/步 - loss: 0.8979 - sparse_categorical_accuracy: 0.6386

1568/未知 655秒 416毫秒/步 - loss: 0.8978 - sparse_categorical_accuracy: 0.6387

1569/未知 656秒 416毫秒/步 - loss: 0.8977 - sparse_categorical_accuracy: 0.6387

1570/未知 656秒 416毫秒/步 - loss: 0.8975 - sparse_categorical_accuracy: 0.6388

1571/未知 656秒 416毫秒/步 - loss: 0.8974 - sparse_categorical_accuracy: 0.6388

1572/未知 657秒 416毫秒/步 - loss: 0.8973 - sparse_categorical_accuracy: 0.6388

1573/未知 657秒 416毫秒/步 - loss: 0.8972 - sparse_categorical_accuracy: 0.6389

1574/未知 658秒 416毫秒/步 - loss: 0.8971 - sparse_categorical_accuracy: 0.6389

1575/未知 658秒 416毫秒/步 - loss: 0.8970 - sparse_categorical_accuracy: 0.6389

1576/未知 659秒 416毫秒/步 - loss: 0.8969 - sparse_categorical_accuracy: 0.6390

1577/未知 659秒 416毫秒/步 - loss: 0.8967 - sparse_categorical_accuracy: 0.6390

1578/未知 660秒 416毫秒/步 - loss: 0.8966 - sparse_categorical_accuracy: 0.6391

1579/未知 660秒 416毫秒/步 - loss: 0.8965 - sparse_categorical_accuracy: 0.6391

1580/未知 661秒 416毫秒/步 - loss: 0.8964 - sparse_categorical_accuracy: 0.6391

1581/未知 661秒 416毫秒/步 - loss: 0.8963 - sparse_categorical_accuracy: 0.6392

1582/未知 662秒 416毫秒/步 - loss: 0.8962 - sparse_categorical_accuracy: 0.6392

1583/未知 662秒 417毫秒/步 - loss: 0.8961 - sparse_categorical_accuracy: 0.6392

1584/未知 662秒 417毫秒/步 - loss: 0.8959 - sparse_categorical_accuracy: 0.6393

1585/未知 663秒 417毫秒/步 - loss: 0.8958 - sparse_categorical_accuracy: 0.6393

1586/未知 663秒 417毫秒/步 - loss: 0.8957 - sparse_categorical_accuracy: 0.6394

1587/未知 664s 417ms/step - 损失: 0.8956 - 稀疏类别准确率: 0.6394

1588/未知 664s 417ms/step - 损失: 0.8955 - 稀疏类别准确率: 0.6394

1589/未知 665s 417ms/step - 损失: 0.8954 - 稀疏类别准确率: 0.6395

1590/未知 665s 417ms/step - 损失: 0.8953 - 稀疏类别准确率: 0.6395

1591/未知 666s 417ms/step - 损失: 0.8952 - 稀疏类别准确率: 0.6395

1592/未知 666s 417ms/step - 损失: 0.8950 - 稀疏类别准确率: 0.6396

1593/未知 666s 417ms/step - 损失: 0.8949 - 稀疏类别准确率: 0.6396

1594/未知 667s 417ms/step - 损失: 0.8948 - 稀疏类别准确率: 0.6397

1595/未知 667s 417ms/step - 损失: 0.8947 - 稀疏类别准确率: 0.6397

1596/未知 668s 417ms/step - 损失: 0.8946 - 稀疏类别准确率: 0.6397

1597/未知 668s 417ms/step - 损失: 0.8945 - 稀疏类别准确率: 0.6398

1598/未知 669s 417ms/step - 损失: 0.8944 - 稀疏类别准确率: 0.6398

1599/未知 669s 417ms/step - 损失: 0.8943 - 稀疏类别准确率: 0.6398

1600/未知 669s 417ms/step - 损失: 0.8941 - 稀疏类别准确率: 0.6399

1601/未知 670s 417ms/step - 损失: 0.8940 - 稀疏类别准确率: 0.6399

1602/未知 670s 417ms/step - 损失: 0.8939 - 稀疏类别准确率: 0.6400

1603/未知 671s 417ms/step - 损失: 0.8938 - 稀疏类别准确率: 0.6400

1604/未知 671s 417ms/step - 损失: 0.8937 - 稀疏类别准确率: 0.6400

1605/未知 672s 417ms/step - 损失: 0.8936 - 稀疏类别准确率: 0.6401

1606/未知 672s 417ms/step - 损失: 0.8935 - 稀疏类别准确率: 0.6401

1607/未知 673s 417ms/step - 损失: 0.8934 - 稀疏类别准确率: 0.6401

1608/未知 673s 417ms/step - 损失: 0.8933 - 稀疏类别准确率: 0.6402

1609/未知 673s 417ms/step - 损失: 0.8931 - 稀疏类别准确率: 0.6402

1610/未知 674s 417ms/step - 损失: 0.8930 - 稀疏类别准确率: 0.6403

1611/未知 674s 417ms/step - 损失: 0.8929 - 稀疏类别准确率: 0.6403

1612/未知 675s 417ms/step - 损失: 0.8928 - 稀疏类别准确率: 0.6403

1613/未知 675s 417ms/step - 损失: 0.8927 - 稀疏类别准确率: 0.6404

1614/未知 675s 417ms/step - 损失: 0.8926 - 稀疏类别准确率: 0.6404

1615/未知 676s 417ms/step - 损失: 0.8925 - 稀疏类别准确率: 0.6404

1616/未知 676s 417ms/step - 损失: 0.8924 - 稀疏类别准确率: 0.6405

1617/未知 677s 417ms/step - 损失: 0.8923 - 稀疏类别准确率: 0.6405

1618/未知 677s 417ms/step - 损失: 0.8922 - 稀疏类别准确率: 0.6405

1619/未知 677s 417ms/step - 损失: 0.8920 - 稀疏类别准确率: 0.6406

1620/未知 678s 417ms/step - 损失: 0.8919 - 稀疏类别准确率: 0.6406

1621/未知 678s 417ms/step - 损失: 0.8918 - 稀疏类别准确率: 0.6407

1622/未知 678s 417ms/step - 损失: 0.8917 - 稀疏类别准确率: 0.6407

1623/未知 679s 417ms/step - 损失: 0.8916 - 稀疏类别准确率: 0.6407

1624/未知 679s 417ms/step - 损失: 0.8915 - 稀疏类别准确率: 0.6408

1625/未知 679s 416ms/step - 损失: 0.8914 - 稀疏类别准确率: 0.6408

1626/未知 680s 416ms/step - 损失: 0.8913 - 稀疏类别准确率: 0.6408

1627/未知 680s 417ms/step - 损失: 0.8912 - 稀疏类别准确率: 0.6409

1628/未知 681s 417ms/step - 损失: 0.8911 - 稀疏类别准确率: 0.6409

1629/未知 681s 417ms/step - 损失: 0.8909 - 稀疏类别准确率: 0.6409

1630/未知 682s 417ms/step - 损失: 0.8908 - 稀疏类别准确率: 0.6410

1631/未知 682s 417ms/step - 损失: 0.8907 - 稀疏类别准确率: 0.6410

1632/未知 683s 417ms/step - 损失: 0.8906 - 稀疏类别准确率: 0.6411

1633/未知 683s 417ms/step - 损失: 0.8905 - 稀疏类别准确率: 0.6411

1634/未知 684s 417ms/step - 损失: 0.8904 - 稀疏类别准确率: 0.6411

1635/未知 684s 417ms/step - 损失: 0.8903 - 稀疏类别准确率: 0.6412

1636/未知 685s 417ms/step - 损失: 0.8902 - 稀疏类别准确率: 0.6412

1637/未知 685s 417ms/step - 损失: 0.8901 - 稀疏类别准确率: 0.6412

1638/未知 686s 417ms/step - 损失: 0.8900 - 稀疏类别准确率: 0.6413

1639/未知 686s 417ms/step - 损失: 0.8899 - 稀疏类别准确率: 0.6413

1640/未知 686s 417ms/step - 损失: 0.8898 - 稀疏类别准确率: 0.6413

1641/未知 687s 417ms/step - 损失: 0.8897 - 稀疏类别准确率: 0.6414

1642/未知 687s 417ms/step - 损失: 0.8895 - 稀疏类别准确率: 0.6414

1643/未知 688s 417ms/step - 损失: 0.8894 - 稀疏类别准确率: 0.6414

1644/未知 688s 417ms/step - 损失: 0.8893 - 稀疏类别准确率: 0.6415

1645/未知 689s 417ms/step - 损失: 0.8892 - 稀疏类别准确率: 0.6415

1646/未知 689s 417ms/step - 损失: 0.8891 - 稀疏类别准确率: 0.6416

1647/未知 690s 417ms/step - 损失: 0.8890 - 稀疏类别准确率: 0.6416

1648/未知 690s 417ms/step - 损失: 0.8889 - 稀疏类别准确率: 0.6416

1649/未知 690s 417ms/step - 损失: 0.8888 - 稀疏类别准确率: 0.6417

1650/未知 691s 417ms/step - 损失: 0.8887 - 稀疏类别准确率: 0.6417

1651/未知 691s 417ms/step - 损失: 0.8886 - 稀疏类别准确率: 0.6417

1652/未知 692s 417ms/step - 损失: 0.8885 - 稀疏类别准确率: 0.6418

1653/未知 692s 417ms/step - 损失: 0.8884 - 稀疏类别准确率: 0.6418

1654/未知 693s 417ms/step - 损失: 0.8883 - 稀疏类别准确率: 0.6418

1655/未知 693s 417ms/step - 损失: 0.8882 - 稀疏类别准确率: 0.6419

1656/未知 693s 417ms/step - 损失: 0.8880 - 稀疏类别准确率: 0.6419

1657/未知 694s 417ms/step - 损失: 0.8879 - 稀疏类别准确率: 0.6419

1658/未知 694s 417ms/step - 损失: 0.8878 - 稀疏类别准确率: 0.6420

1659/未知 695s 417ms/step - 损失: 0.8877 - 稀疏类别准确率: 0.6420

1660/未知 695s 417ms/step - 损失: 0.8876 - 稀疏类别准确率: 0.6420

1661/未知 695s 417ms/step - 损失: 0.8875 - 稀疏类别准确率: 0.6421

1662/未知 696s 417ms/step - 损失: 0.8874 - 稀疏类别准确率: 0.6421

1663/未知 696s 417ms/step - 损失: 0.8873 - 稀疏类别准确率: 0.6422

1664/未知 696s 417ms/step - 损失: 0.8872 - 稀疏类别准确率: 0.6422

1665/未知 697s 417ms/step - 损失: 0.8871 - 稀疏类别准确率: 0.6422

1666/未知 697s 417ms/step - 损失: 0.8870 - 稀疏类别准确率: 0.6423

1667/未知 698s 417ms/step - 损失: 0.8869 - 稀疏类别准确率: 0.6423

1668/未知 698s 417ms/step - 损失: 0.8868 - 稀疏类别准确率: 0.6423

1669/未知 698s 417ms/step - 损失: 0.8867 - 稀疏类别准确率: 0.6424

1670/未知 699s 417ms/step - 损失: 0.8866 - 稀疏类别准确率: 0.6424

1671/未知 699s 417ms/step - 损失: 0.8865 - 稀疏类别准确率: 0.6424

1672/未知 700s 417ms/step - 损失: 0.8864 - 稀疏类别准确率: 0.6425

1673/未知 700s 417ms/step - 损失: 0.8863 - 稀疏类别准确率: 0.6425

1674/未知 700s 417ms/step - 损失: 0.8862 - 稀疏类别准确率: 0.6425

1675/未知 701s 417ms/step - 损失: 0.8861 - 稀疏类别准确率: 0.6426

1676/未知 701s 417ms/step - 损失: 0.8859 - 稀疏类别准确率: 0.6426

1677/未知 702s 417ms/step - 损失: 0.8858 - 稀疏类别准确率: 0.6426

1678/未知 702s 417ms/step - 损失: 0.8857 - 稀疏类别准确率: 0.6427

1679/未知 703s 417ms/step - 损失: 0.8856 - 稀疏类别准确率: 0.6427

1680/未知 703s 417ms/step - 损失: 0.8855 - 稀疏类别准确率: 0.6427

1681/未知 704s 417ms/step - 损失: 0.8854 - 稀疏类别准确率: 0.6428

1682/未知 704s 417ms/step - 损失: 0.8853 - 稀疏类别准确率: 0.6428

1683/未知 705s 417ms/step - 损失: 0.8852 - 稀疏类别准确率: 0.6428

1684/未知 705s 417ms/step - 损失: 0.8851 - 稀疏类别准确率: 0.6429

1685/未知 706s 417ms/step - 损失: 0.8850 - 稀疏类别准确率: 0.6429

1686/未知 706s 417ms/step - 损失: 0.8849 - 稀疏类别准确率: 0.6429

1687/未知 706s 417ms/step - 损失: 0.8848 - 稀疏类别准确率: 0.6430

1688/未知 707s 417ms/step - 损失: 0.8847 - 稀疏类别准确率: 0.6430

1689/未知 707s 417ms/step - 损失: 0.8846 - 稀疏类别准确率: 0.6431

1690/未知 708s 417ms/step - 损失: 0.8845 - 稀疏类别准确率: 0.6431

1691/未知 708s 417ms/step - 损失: 0.8844 - 稀疏类别准确率: 0.6431

1692/未知 709s 417ms/step - 损失: 0.8843 - 稀疏类别准确率: 0.6432

1693/未知 709s 417ms/step - 损失: 0.8842 - 稀疏类别准确率: 0.6432

1694/未知 709s 417ms/step - 损失: 0.8841 - 稀疏类别准确率: 0.6432

1695/未知 710s 417ms/step - 损失: 0.8840 - 稀疏类别准确率: 0.6433

1696/未知 710s 417ms/step - 损失: 0.8839 - 稀疏类别准确率: 0.6433

1697/未知 711s 417ms/step - 损失: 0.8838 - 稀疏类别准确率: 0.6433

1698/未知 711s 417ms/step - 损失: 0.8837 - 稀疏类别准确率: 0.6434

1699/未知 711s 417ms/step - 损失: 0.8836 - 稀疏类别准确率: 0.6434

1700/未知 712s 417ms/step - 损失: 0.8835 - 稀疏类别准确率: 0.6434

1701/未知 712s 417ms/step - 损失: 0.8834 - 稀疏类别准确率: 0.6435

1702/未知 713s 417ms/step - 损失: 0.8833 - 稀疏类别准确率: 0.6435

1703/未知 713s 417ms/step - 损失: 0.8832 - 稀疏类别准确率: 0.6435

1704/未知 713s 417ms/step - 损失: 0.8831 - 稀疏类别准确率: 0.6436

1705/未知 714s 417ms/step - 损失: 0.8830 - 稀疏类别准确率: 0.6436

1706/未知 714s 417ms/step - 损失: 0.8829 - 稀疏类别准确率: 0.6436

1707/未知 714s 417ms/step - 损失: 0.8828 - 稀疏类别准确率: 0.6437

1708/未知 715s 417ms/step - 损失: 0.8827 - 稀疏类别准确率: 0.6437

1709/未知 715s 417ms/step - 损失: 0.8826 - 稀疏类别准确率: 0.6437

1710/未知 716s 417ms/step - 损失: 0.8825 - 稀疏类别准确率: 0.6438

1711/未知 716s 417ms/step - 损失: 0.8824 - 稀疏类别准确率: 0.6438

1712/未知 717s 417ms/step - 损失: 0.8823 - 稀疏类别准确率: 0.6438

1713/未知 717s 417ms/step - 损失: 0.8822 - 稀疏类别准确率: 0.6439

1714/未知 718s 417ms/step - 损失: 0.8821 - 稀疏类别准确率: 0.6439

1715/未知 718s 417ms/step - 损失: 0.8820 - 稀疏类别准确率: 0.6439

1716/未知 719s 417ms/step - 损失: 0.8818 - 稀疏类别准确率: 0.6440

1717/未知 719s 417ms/step - 损失: 0.8817 - 稀疏类别准确率: 0.6440

1718/未知 719s 417ms/step - 损失: 0.8816 - 稀疏类别准确率: 0.6440

1719/未知 720s 417ms/step - 损失: 0.8815 - 稀疏类别准确率: 0.6441

1720/未知 720s 417ms/step - 损失: 0.8814 - 稀疏类别准确率: 0.6441

1721/未知 720s 417ms/step - 损失: 0.8813 - 稀疏类别准确率: 0.6441

1722/未知 721s 417ms/step - 损失: 0.8812 - 稀疏类别准确率: 0.6442

1723/未知 721s 417ms/step - 损失: 0.8811 - 稀疏类别准确率: 0.6442

1724/未知 722s 417ms/step - 损失: 0.8810 - 稀疏类别准确率: 0.6442

1725/未知 722s 417ms/step - 损失: 0.8809 - 稀疏类别准确率: 0.6443

1726/未知 722s 417ms/step - 损失: 0.8808 - 稀疏类别准确率: 0.6443

1727/未知 723s 417ms/step - 损失: 0.8807 - 稀疏类别准确率: 0.6443

1728/未知 723s 417ms/step - 损失: 0.8806 - 稀疏类别准确率: 0.6444

1729/未知 723s 417ms/step - 损失: 0.8805 - 稀疏类别准确率: 0.6444

1730/未知 724s 417ms/step - 损失: 0.8804 - 稀疏类别准确率: 0.6444

1731/未知 724s 417ms/step - 损失: 0.8804 - 稀疏类别准确率: 0.6445

1732/未知 725s 417ms/step - 损失: 0.8803 - 稀疏类别准确率: 0.6445

1733/未知 725s 417ms/step - 损失: 0.8802 - 稀疏类别准确率: 0.6445

1734/未知 726s 417ms/step - 损失: 0.8801 - 稀疏类别准确率: 0.6446

1735/未知 726s 417ms/step - 损失: 0.8800 - 稀疏类别准确率: 0.6446

1736/未知 727s 417ms/step - 损失: 0.8799 - 稀疏类别准确率: 0.6446

1737/未知 727s 417ms/step - 损失: 0.8798 - 稀疏类别准确率: 0.6447

1738/未知 727s 417ms/step - 损失: 0.8797 - 稀疏类别准确率: 0.6447

1739/未知 728s 417ms/step - 损失: 0.8796 - 稀疏类别准确率: 0.6447

1740/未知 728s 417ms/step - 损失: 0.8795 - 稀疏类别准确率: 0.6448

1741/未知 729s 417ms/step - 损失: 0.8794 - 稀疏类别准确率: 0.6448

1742/未知 729s 417ms/step - 损失: 0.8793 - 稀疏类别准确率: 0.6448

1743/未知 730s 417ms/step - 损失: 0.8792 - 稀疏类别准确率: 0.6449

1744/未知 730s 417ms/step - 损失: 0.8791 - 稀疏类别准确率: 0.6449

1745/未知 730s 417ms/step - 损失: 0.8790 - 稀疏类别准确率: 0.6449

1746/未知 731s 417ms/step - 损失: 0.8789 - 稀疏类别准确率: 0.6450

1747/未知 731s 417ms/step - 损失: 0.8788 - 稀疏类别准确率: 0.6450

1748/未知 731s 417ms/step - 损失: 0.8787 - 稀疏类别准确率: 0.6450

1749/未知 732s 417ms/step - 损失: 0.8786 - 稀疏类别准确率: 0.6451

1750/未知 732s 417ms/step - 损失: 0.8785 - 稀疏类别准确率: 0.6451

1751/未知 733s 417ms/step - 损失: 0.8784 - 稀疏类别准确率: 0.6451

1752/未知 733s 417ms/step - 损失: 0.8783 - 稀疏类别准确率: 0.6452

1753/未知 733s 417ms/step - 损失: 0.8782 - 稀疏类别准确率: 0.6452

1754/未知 734s 417ms/step - 损失: 0.8781 - 稀疏类别准确率: 0.6452

1755/未知 734s 417ms/step - 损失: 0.8780 - 稀疏类别准确率: 0.6453

1756/未知 735s 417ms/step - 损失: 0.8779 - 稀疏类别准确率: 0.6453

1757/未知 735s 417ms/step - 损失: 0.8778 - 稀疏类别准确率: 0.6453

1758/未知 736s 417ms/step - 损失: 0.8777 - 稀疏类别准确率: 0.6453

1759/未知 736s 417ms/step - 损失: 0.8776 - 稀疏类别准确率: 0.6454

1760/未知 737s 417ms/step - 损失: 0.8775 - 稀疏类别准确率: 0.6454

1761/未知 737s 417ms/step - 损失: 0.8774 - 稀疏类别准确率: 0.6454

1762/未知 738s 417ms/step - 损失: 0.8773 - 稀疏类别准确率: 0.6455

1763/未知 738s 417ms/step - 损失: 0.8772 - 稀疏类别准确率: 0.6455

1764/未知 738s 417ms/step - 损失: 0.8771 - 稀疏类别准确率: 0.6455

1765/未知 739s 417ms/step - 损失: 0.8770 - 稀疏类别准确率: 0.6456

1766/未知 739s 417ms/step - 损失: 0.8769 - 稀疏类别准确率: 0.6456

1767/未知 739s 417ms/step - 损失: 0.8768 - 稀疏类别准确率: 0.6456

1768/未知 740s 417ms/step - 损失: 0.8767 - 稀疏类别准确率: 0.6457

1769/未知 740s 417ms/step - 损失: 0.8766 - 稀疏类别准确率: 0.6457

1770/未知 741s 417ms/step - 损失: 0.8765 - 稀疏类别准确率: 0.6457

1771/未知 741s 417ms/step - 损失: 0.8764 - 稀疏类别准确率: 0.6458

1772/未知 741s 417ms/step - 损失: 0.8763 - 稀疏类别准确率: 0.6458

1773/未知 742s 417ms/step - 损失: 0.8763 - 稀疏类别准确率: 0.6458

1774/未知 742s 417ms/step - 损失: 0.8762 - 稀疏类别准确率: 0.6459

1775/未知 743s 417ms/step - 损失: 0.8761 - 稀疏类别准确率: 0.6459

1776/未知 743s 417ms/step - 损失: 0.8760 - 稀疏类别准确率: 0.6459

1777/未知 743s 417ms/step - 损失: 0.8759 - 稀疏类别准确率: 0.6460

1778/未知 744s 417ms/step - 损失: 0.8758 - 稀疏类别准确率: 0.6460

1779/未知 744s 417ms/step - 损失: 0.8757 - 稀疏类别准确率: 0.6460

1780/未知 745s 417ms/step - 损失: 0.8756 - 稀疏类别准确率: 0.6461

1781/未知 745s 417ms/step - 损失: 0.8755 - 稀疏类别准确率: 0.6461

1782/未知 746s 417ms/step - 损失: 0.8754 - 稀疏类别准确率: 0.6461

1783/未知 746s 417ms/step - 损失: 0.8753 - 稀疏类别准确率: 0.6461

1784/未知 747s 417ms/step - 损失: 0.8752 - 稀疏类别准确率: 0.6462

1785/未知 747s 417ms/step - 损失: 0.8751 - 稀疏类别准确率: 0.6462

1786/未知 747s 417ms/step - 损失: 0.8750 - 稀疏类别准确率: 0.6462

1787/未知 748s 417ms/step - 损失: 0.8749 - 稀疏类别准确率: 0.6463

1788/未知 748s 417ms/step - 损失: 0.8748 - 稀疏类别准确率: 0.6463

1789/未知 749s 417ms/step - 损失: 0.8747 - 稀疏类别准确率: 0.6463

1790/未知 749s 417ms/step - 损失: 0.8746 - 稀疏类别准确率: 0.6464

1791/未知 750s 417ms/step - 损失: 0.8745 - 稀疏类别准确率: 0.6464

1792/未知 750s 417ms/step - 损失: 0.8744 - 稀疏类别准确率: 0.6464

1793/未知 751s 417ms/step - 损失: 0.8743 - 稀疏类别准确率: 0.6465

1794/未知 751s 417ms/step - 损失: 0.8743 - 稀疏类别准确率: 0.6465

1795/未知 752s 417ms/step - 损失: 0.8742 - 稀疏类别准确率: 0.6465

1796/未知 752s 417ms/step - 损失: 0.8741 - 稀疏类别准确率: 0.6466

1797/未知 753s 417ms/step - 损失: 0.8740 - 稀疏类别准确率: 0.6466

1798/未知 753s 417ms/step - 损失: 0.8739 - 稀疏类别准确率: 0.6466

1799/未知 753s 417ms/step - 损失: 0.8738 - 稀疏类别准确率: 0.6466

1800/未知 754s 417ms/step - 损失: 0.8737 - 稀疏类别准确率: 0.6467

1801/未知 754s 417ms/step - 损失: 0.8736 - 稀疏类别准确率: 0.6467

1802/未知 755s 417ms/step - 损失: 0.8735 - 稀疏类别准确率: 0.6467

1803/未知 755s 417ms/step - 损失: 0.8734 - 稀疏类别准确率: 0.6468

1804/未知 756s 417ms/step - 损失: 0.8733 - 稀疏类别准确率: 0.6468

1805/未知 756s 417ms/step - 损失: 0.8732 - 稀疏类别准确率: 0.6468

1806/未知 757s 417ms/step - 损失: 0.8731 - 稀疏类别准确率: 0.6469

1807/未知 757s 417ms/step - 损失: 0.8730 - 稀疏类别准确率: 0.6469

1808/未知 757s 417ms/step - 损失: 0.8729 - 稀疏类别准确率: 0.6469

1809/未知 758s 417ms/step - 损失: 0.8729 - 稀疏类别准确率: 0.6470

1810/未知 758s 417ms/step - 损失: 0.8728 - 稀疏类别准确率: 0.6470

1811/未知 758s 417ms/step - 损失: 0.8727 - 稀疏类别准确率: 0.6470

1812/未知 759s 417ms/step - 损失: 0.8726 - 稀疏类别准确率: 0.6471

1813/未知 759s 417ms/step - 损失: 0.8725 - 稀疏类别准确率: 0.6471

1814/未知 760s 417ms/step - 损失: 0.8724 - 稀疏类别准确率: 0.6471

1815/未知 760s 417ms/step - 损失: 0.8723 - 稀疏类别准确率: 0.6471

1816/未知 760s 417ms/step - 损失: 0.8722 - 稀疏类别准确率: 0.6472

1817/未知 761s 417ms/step - 损失: 0.8721 - 稀疏类别准确率: 0.6472

1818/未知 761s 417ms/step - 损失: 0.8720 - 稀疏类别准确率: 0.6472

1819/未知 761s 417ms/step - 损失: 0.8719 - 稀疏类别准确率: 0.6473

1820/未知 762s 417ms/step - 损失: 0.8718 - 稀疏类别准确率: 0.6473

1821/未知 762s 417ms/step - 损失: 0.8717 - 稀疏类别准确率: 0.6473

1822/未知 763s 417ms/step - 损失: 0.8717 - 稀疏类别准确率: 0.6474

1823/未知 763s 417ms/step - 损失: 0.8716 - 稀疏类别准确率: 0.6474

1824/未知 764s 417ms/step - 损失: 0.8715 - 稀疏类别准确率: 0.6474

1825/未知 764s 417ms/step - 损失: 0.8714 - 稀疏类别准确率: 0.6475

1826/未知 765s 417ms/step - 损失: 0.8713 - 稀疏类别准确率: 0.6475

1827/未知 765s 417ms/step - 损失: 0.8712 - 稀疏类别准确率: 0.6475

1828/未知 766s 417ms/step - 损失: 0.8711 - 稀疏类别准确率: 0.6475

1829/未知 766s 417ms/step - 损失: 0.8710 - 稀疏类别准确率: 0.6476

1830/未知 767s 417ms/step - 损失: 0.8709 - 稀疏类别准确率: 0.6476

1831/未知 767s 417ms/step - 损失: 0.8708 - 稀疏类别准确率: 0.6476

1832/未知 767s 417ms/step - 损失: 0.8707 - 稀疏类别准确率: 0.6477

1833/未知 768s 417ms/step - 损失: 0.8706 - 稀疏类别准确率: 0.6477

1834/未知 768s 417ms/step - 损失: 0.8706 - 稀疏类别准确率: 0.6477

1835/未知 769s 418ms/step - 损失: 0.8705 - 稀疏类别准确率: 0.6478

1836/未知 769s 418ms/step - 损失: 0.8704 - 稀疏类别准确率: 0.6478

1837/未知 770s 418ms/step - 损失: 0.8703 - 稀疏类别准确率: 0.6478

1838/未知 770s 418ms/step - 损失: 0.8702 - 稀疏类别准确率: 0.6478

1839/未知 771s 418ms/step - 损失: 0.8701 - 稀疏类别准确率: 0.6479

1840/未知 771s 418ms/step - 损失: 0.8700 - 稀疏类别准确率: 0.6479

1841/未知 771s 417ms/step - 损失: 0.8699 - 稀疏类别准确率: 0.6479

1842/未知 772s 417ms/step - 损失: 0.8698 - 稀疏类别准确率: 0.6480

1843/未知 772s 417ms/step - 损失: 0.8697 - 稀疏类别准确率: 0.6480

1844/未知 772s 417ms/step - 损失: 0.8696 - 稀疏类别准确率: 0.6480

1845/未知 773s 417ms/step - 损失: 0.8696 - 稀疏类别准确率: 0.6481

1846/未知 773s 417ms/step - 损失: 0.8695 - 稀疏类别准确率: 0.6481

1847/未知 774s 417ms/step - 损失: 0.8694 - 稀疏类别准确率: 0.6481

1848/未知 774s 417ms/step - 损失: 0.8693 - 稀疏类别准确率: 0.6481

1849/未知 774s 417ms/step - 损失: 0.8692 - 稀疏类别准确率: 0.6482

1850/未知 775s 417ms/step - 损失: 0.8691 - 稀疏类别准确率: 0.6482

1851/未知 775s 417ms/step - 损失: 0.8690 - 稀疏类别准确率: 0.6482

1852/未知 776s 417ms/step - 损失: 0.8689 - 稀疏类别准确率: 0.6483

1853/未知 776s 417ms/step - 损失: 0.8688 - 稀疏类别准确率: 0.6483

1854/未知 777s 417ms/step - 损失: 0.8688 - 稀疏类别准确率: 0.6483

1855/未知 777s 417ms/step - 损失: 0.8687 - 稀疏类别准确率: 0.6484

1856/未知 778s 417ms/step - 损失: 0.8686 - 稀疏类别准确率: 0.6484

1857/未知 778s 417ms/step - 损失: 0.8685 - 稀疏类别准确率: 0.6484

1858/未知 778s 417ms/step - 损失: 0.8684 - 稀疏类别准确率: 0.6484

1859/未知 779s 417ms/step - 损失: 0.8683 - 稀疏类别准确率: 0.6485

1860/未知 779s 417ms/step - 损失: 0.8682 - 稀疏类别准确率: 0.6485

1861/未知 779s 417ms/step - 损失: 0.8681 - 稀疏类别准确率: 0.6485

1862/未知 780s 417ms/step - 损失: 0.8680 - 稀疏类别准确率: 0.6486

1863/未知 780s 417ms/step - 损失: 0.8679 - 稀疏类别准确率: 0.6486

1864/未知 781s 417ms/step - 损失: 0.8679 - 稀疏类别准确率: 0.6486

1865/未知 781s 417ms/step - 损失: 0.8678 - 稀疏类别准确率: 0.6486

1865/1865 ━━━━━━━━━━━━━━━━━━━━ 781s 417ms/step - 损失: 0.8677 - 稀疏类别准确率: 0.6487

Model training finished

/home/humbulani/tensorflow-env/env/lib/python3.11/site-packages/keras/src/trainers/epoch_iterator.py:151: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
  self._interrupted_warning()

Test accuracy: 74.5%

宽深模型在测试集上达到了约 79% 的准确率。

实验 3：Deep & Cross 模型

在第三个实验中，我们构建了一个 Deep & Cross 模型。这个模型的深度部分与上一个实验中创建的深度部分相同。交叉部分的核心思想是以高效的方式应用显式的特征交叉，其中交叉特征的阶数随着层深度增长。

def create_deep_and_cross_model():
    inputs = create_model_inputs()
    x0 = encode_inputs(inputs, use_embedding=True)

    cross = x0
    for _ in hidden_units:
        units = cross.shape[-1]
        x = layers.Dense(units)(cross)
        cross = x0 * x + cross
    cross = layers.BatchNormalization()(cross)

    deep = x0
    for units in hidden_units:
        deep = layers.Dense(units)(deep)
        deep = layers.BatchNormalization()(deep)
        deep = layers.ReLU()(deep)
        deep = layers.Dropout(dropout_rate)(deep)

    merged = layers.concatenate([cross, deep])
    outputs = layers.Dense(units=NUM_CLASSES, activation="softmax")(merged)
    model = keras.Model(inputs=inputs, outputs=outputs)
    return model


deep_and_cross_model = create_deep_and_cross_model()
keras.utils.plot_model(deep_and_cross_model, show_shapes=True, rankdir="LR")

png

运行它

run_experiment(deep_and_cross_model)

Start training the model...

  1/Unknown  1s 993ms/step - loss: 2.4838 - sparse_categorical_accuracy: 0.1057


  2/Unknown  1s 465ms/step - loss: 2.4552 - sparse_categorical_accuracy: 0.1113


  3/Unknown  2s 483ms/step - loss: 2.4419 - sparse_categorical_accuracy: 0.1124


  4/Unknown  2s 462ms/step - loss: 2.4248 - sparse_categorical_accuracy: 0.1140


  5/Unknown  3s 468ms/step - loss: 2.4071 - sparse_categorical_accuracy: 0.1150


  6/Unknown  3s 460ms/step - loss: 2.3918 - sparse_categorical_accuracy: 0.1176


  7/Unknown  4s 467ms/step - loss: 2.3763 - sparse_categorical_accuracy: 0.1209


  8/Unknown  4s 466ms/step - loss: 2.3613 - sparse_categorical_accuracy: 0.1243


  9/Unknown  5s 467ms/step - loss: 2.3470 - sparse_categorical_accuracy: 0.1277


 10/Unknown  5s 465ms/step - loss: 2.3333 - sparse_categorical_accuracy: 0.1311


 11/Unknown  6s 540ms/step - loss: 2.3202 - sparse_categorical_accuracy: 0.1346


 12/Unknown  7s 558ms/step - loss: 2.3077 - sparse_categorical_accuracy: 0.1380


 13/Unknown  8s 554ms/step - loss: 2.2955 - sparse_categorical_accuracy: 0.1414


 14/Unknown  8s 549ms/step - loss: 2.2834 - sparse_categorical_accuracy: 0.1451


 15/Unknown  9s 545ms/step - loss: 2.2716 - sparse_categorical_accuracy: 0.1489


 16/Unknown  9s 540ms/step - loss: 2.2602 - sparse_categorical_accuracy: 0.1526


 17/Unknown  10s 535ms/step - loss: 2.2494 - sparse_categorical_accuracy: 0.1562


 18/Unknown  10s 532ms/step - loss: 2.2387 - sparse_categorical_accuracy: 0.1598


 19/Unknown  11s 528ms/step - loss: 2.2280 - sparse_categorical_accuracy: 0.1634


 20/Unknown  11s 524ms/step - loss: 2.2174 - sparse_categorical_accuracy: 0.1672


 21/Unknown  11s 520ms/step - loss: 2.2071 - sparse_categorical_accuracy: 0.1707


 22/Unknown  12s 518ms/step - loss: 2.1971 - sparse_categorical_accuracy: 0.1742


 23/Unknown  12s 514ms/step - loss: 2.1872 - sparse_categorical_accuracy: 0.1778


 24/Unknown  13s 513ms/step - loss: 2.1775 - sparse_categorical_accuracy: 0.1813


 25/Unknown  13s 513ms/step - loss: 2.1680 - sparse_categorical_accuracy: 0.1848


 26/Unknown  14s 512ms/step - loss: 2.1587 - sparse_categorical_accuracy: 0.1882


 27/Unknown  14s 509ms/step - loss: 2.1495 - sparse_categorical_accuracy: 0.1917


 28/Unknown  15s 509ms/step - loss: 2.1405 - sparse_categorical_accuracy: 0.1951


 29/Unknown  15s 508ms/step - loss: 2.1316 - sparse_categorical_accuracy: 0.1986


 30/Unknown  16s 505ms/step - loss: 2.1228 - sparse_categorical_accuracy: 0.2020


 31/Unknown  16s 504ms/step - loss: 2.1142 - sparse_categorical_accuracy: 0.2054


 32/Unknown  17s 502ms/step - loss: 2.1056 - sparse_categorical_accuracy: 0.2089


 33/Unknown  17s 502ms/step - loss: 2.0971 - sparse_categorical_accuracy: 0.2123


 34/Unknown  18s 502ms/step - loss: 2.0888 - sparse_categorical_accuracy: 0.2156


 35/Unknown  18s 500ms/step - loss: 2.0807 - sparse_categorical_accuracy: 0.2190


 36/Unknown  18s 497ms/step - loss: 2.0726 - sparse_categorical_accuracy: 0.2223


 37/Unknown  19s 499ms/step - loss: 2.0646 - sparse_categorical_accuracy: 0.2257


 38/Unknown  19s 497ms/step - loss: 2.0567 - sparse_categorical_accuracy: 0.2290


 39/Unknown  20s 495ms/step - loss: 2.0490 - sparse_categorical_accuracy: 0.2322


 40/Unknown  20s 494ms/step - loss: 2.0414 - sparse_categorical_accuracy: 0.2354


 41/Unknown  21s 490ms/step - loss: 2.0339 - sparse_categorical_accuracy: 0.2386


 42/Unknown  21s 487ms/step - loss: 2.0265 - sparse_categorical_accuracy: 0.2417


 43/Unknown  21s 485ms/step - loss: 2.0192 - sparse_categorical_accuracy: 0.2448


 44/Unknown  22s 483ms/step - loss: 2.0120 - sparse_categorical_accuracy: 0.2479


 45/Unknown  22s 482ms/step - loss: 2.0049 - sparse_categorical_accuracy: 0.2509


 46/Unknown  23s 480ms/step - loss: 1.9980 - sparse_categorical_accuracy: 0.2539


 47/Unknown  23s 479ms/step - loss: 1.9911 - sparse_categorical_accuracy: 0.2569


 48/Unknown  23s 478ms/step - loss: 1.9843 - sparse_categorical_accuracy: 0.2598


 49/Unknown  24s 476ms/step - loss: 1.9777 - sparse_categorical_accuracy: 0.2627


 50/Unknown  24s 475ms/step - loss: 1.9711 - sparse_categorical_accuracy: 0.2655


 51/Unknown  25s 473ms/step - loss: 1.9646 - sparse_categorical_accuracy: 0.2683


 52/Unknown  25s 472ms/step - loss: 1.9581 - sparse_categorical_accuracy: 0.2711


 53/Unknown  26s 473ms/step - loss: 1.9517 - sparse_categorical_accuracy: 0.2739


 54/Unknown  26s 474ms/step - loss: 1.9454 - sparse_categorical_accuracy: 0.2766


 55/Unknown  27s 474ms/step - loss: 1.9392 - sparse_categorical_accuracy: 0.2793


 56/Unknown  27s 474ms/step - loss: 1.9331 - sparse_categorical_accuracy: 0.2819


 57/Unknown  28s 474ms/step - loss: 1.9271 - sparse_categorical_accuracy: 0.2845


 58/Unknown  28s 474ms/step - loss: 1.9211 - sparse_categorical_accuracy: 0.2871


 59/Unknown  28s 474ms/step - loss: 1.9152 - sparse_categorical_accuracy: 0.2897


 60/Unknown  29s 473ms/step - loss: 1.9093 - sparse_categorical_accuracy: 0.2922


 61/Unknown  29s 473ms/step - loss: 1.9035 - sparse_categorical_accuracy: 0.2947


 62/Unknown  30s 473ms/step - loss: 1.8977 - sparse_categorical_accuracy: 0.2971


 63/Unknown  30s 472ms/step - loss: 1.8921 - sparse_categorical_accuracy: 0.2996


 64/Unknown  31s 471ms/step - loss: 1.8864 - sparse_categorical_accuracy: 0.3020


 65/Unknown  31s 471ms/step - loss: 1.8809 - sparse_categorical_accuracy: 0.3043


 66/Unknown  32s 470ms/step - loss: 1.8754 - sparse_categorical_accuracy: 0.3067


 67/Unknown  32s 471ms/step - loss: 1.8699 - sparse_categorical_accuracy: 0.3090


 68/Unknown  32s 470ms/step - loss: 1.8645 - sparse_categorical_accuracy: 0.3112


 69/Unknown  33s 471ms/step - loss: 1.8592 - sparse_categorical_accuracy: 0.3135


 70/Unknown  33s 470ms/step - loss: 1.8540 - sparse_categorical_accuracy: 0.3157


 71/Unknown  34s 470ms/step - loss: 1.8487 - sparse_categorical_accuracy: 0.3179


 72/Unknown  34s 470ms/step - loss: 1.8436 - sparse_categorical_accuracy: 0.3201


 73/Unknown  35s 470ms/step - loss: 1.8385 - sparse_categorical_accuracy: 0.3222


 74/Unknown  35s 470ms/step - loss: 1.8335 - sparse_categorical_accuracy: 0.3243


 75/Unknown  36s 470ms/step - loss: 1.8285 - sparse_categorical_accuracy: 0.3264


 76/Unknown  36s 471ms/step - loss: 1.8236 - sparse_categorical_accuracy: 0.3285


 77/Unknown  37s 471ms/step - loss: 1.8187 - sparse_categorical_accuracy: 0.3306


 78/Unknown  37s 471ms/step - loss: 1.8138 - sparse_categorical_accuracy: 0.3326


 79/Unknown  38s 470ms/step - loss: 1.8090 - sparse_categorical_accuracy: 0.3346


 80/Unknown  38s 469ms/step - loss: 1.8042 - sparse_categorical_accuracy: 0.3366


 81/Unknown  38s 468ms/step - loss: 1.7995 - sparse_categorical_accuracy: 0.3385


 82/Unknown  39s 467ms/step - loss: 1.7949 - sparse_categorical_accuracy: 0.3404


 83/Unknown  39s 466ms/step - loss: 1.7903 - sparse_categorical_accuracy: 0.3423


 84/Unknown  40s 466ms/step - loss: 1.7857 - sparse_categorical_accuracy: 0.3442


 85/Unknown  40s 465ms/step - loss: 1.7812 - sparse_categorical_accuracy: 0.3461


 86/Unknown  40s 464ms/step - loss: 1.7767 - sparse_categorical_accuracy: 0.3479


 87/Unknown  41s 463ms/step - loss: 1.7722 - sparse_categorical_accuracy: 0.3497


 88/Unknown  41s 463ms/step - loss: 1.7678 - sparse_categorical_accuracy: 0.3515


 89/Unknown  42s 462ms/step - loss: 1.7635 - sparse_categorical_accuracy: 0.3533


 90/Unknown  42s 462ms/step - loss: 1.7591 - sparse_categorical_accuracy: 0.3550


 91/Unknown  43s 462ms/step - loss: 1.7549 - sparse_categorical_accuracy: 0.3568


 92/Unknown  43s 462ms/step - loss: 1.7506 - sparse_categorical_accuracy: 0.3585


 93/Unknown  44s 462ms/step - loss: 1.7464 - sparse_categorical_accuracy: 0.3602


 94/Unknown  44s 462ms/step - loss: 1.7423 - sparse_categorical_accuracy: 0.3618


 95/Unknown  44s 463ms/step - loss: 1.7381 - sparse_categorical_accuracy: 0.3635


 96/Unknown  45s 463ms/step - loss: 1.7340 - sparse_categorical_accuracy: 0.3651


 97/Unknown  46s 464ms/step - loss: 1.7300 - sparse_categorical_accuracy: 0.3667


 98/Unknown  46s 465ms/step - loss: 1.7259 - sparse_categorical_accuracy: 0.3683


 99/Unknown  47s 465ms/step - loss: 1.7219 - sparse_categorical_accuracy: 0.3699


100/Unknown  47s 465ms/step - loss: 1.7180 - sparse_categorical_accuracy: 0.3715


101/Unknown  47s 465ms/step - loss: 1.7141 - sparse_categorical_accuracy: 0.3730


102/Unknown  48s 464ms/step - loss: 1.7102 - sparse_categorical_accuracy: 0.3745


103/Unknown  48s 464ms/step - loss: 1.7064 - sparse_categorical_accuracy: 0.3760


104/Unknown  49s 464ms/step - loss: 1.7025 - sparse_categorical_accuracy: 0.3775


105/Unknown  49s 465ms/step - loss: 1.6988 - sparse_categorical_accuracy: 0.3790


106/Unknown  50s 465ms/step - loss: 1.6950 - sparse_categorical_accuracy: 0.3804


107/Unknown  50s 465ms/step - loss: 1.6913 - sparse_categorical_accuracy: 0.3819


108/Unknown  51s 465ms/step - loss: 1.6876 - sparse_categorical_accuracy: 0.3833


109/Unknown  51s 465ms/step - loss: 1.6840 - sparse_categorical_accuracy: 0.3847


110/Unknown  52s 464ms/step - loss: 1.6804 - sparse_categorical_accuracy: 0.3861


111/Unknown  52s 463ms/step - loss: 1.6768 - sparse_categorical_accuracy: 0.3874


112/Unknown  52s 462ms/step - loss: 1.6732 - sparse_categorical_accuracy: 0.3888


113/Unknown  53s 461ms/step - loss: 1.6697 - sparse_categorical_accuracy: 0.3901


114/Unknown  53s 461ms/step - loss: 1.6662 - sparse_categorical_accuracy: 0.3914


115/Unknown  53s 460ms/step - loss: 1.6628 - sparse_categorical_accuracy: 0.3927


116/Unknown  54s 459ms/step - loss: 1.6593 - sparse_categorical_accuracy: 0.3940


117/Unknown  54s 459ms/step - loss: 1.6559 - sparse_categorical_accuracy: 0.3953


118/Unknown  55s 458ms/step - loss: 1.6526 - sparse_categorical_accuracy: 0.3966


119/Unknown  55s 458ms/step - loss: 1.6492 - sparse_categorical_accuracy: 0.3979


120/Unknown  55s 457ms/step - loss: 1.6459 - sparse_categorical_accuracy: 0.3991


121/Unknown  56s 458ms/step - loss: 1.6426 - sparse_categorical_accuracy: 0.4003


122/Unknown  56s 458ms/step - loss: 1.6393 - sparse_categorical_accuracy: 0.4016


123/Unknown  57s 458ms/step - loss: 1.6361 - sparse_categorical_accuracy: 0.4028


124/Unknown  57s 458ms/step - loss: 1.6329 - sparse_categorical_accuracy: 0.4040


125/Unknown  58s 459ms/step - loss: 1.6297 - sparse_categorical_accuracy: 0.4052


126/Unknown  58s 459ms/step - loss: 1.6265 - sparse_categorical_accuracy: 0.4063


127/Unknown  59s 459ms/step - loss: 1.6234 - sparse_categorical_accuracy: 0.4075


128/Unknown  59s 459ms/step - loss: 1.6203 - sparse_categorical_accuracy: 0.4087


129/Unknown  60s 459ms/step - loss: 1.6172 - sparse_categorical_accuracy: 0.4098


130/Unknown  60s 459ms/step - loss: 1.6142 - sparse_categorical_accuracy: 0.4109


131/Unknown  61s 459ms/step - loss: 1.6111 - sparse_categorical_accuracy: 0.4121


132/Unknown  61s 458ms/step - loss: 1.6081 - sparse_categorical_accuracy: 0.4132


133/Unknown  61s 457ms/step - loss: 1.6051 - sparse_categorical_accuracy: 0.4143


134/Unknown  62s 457ms/step - loss: 1.6021 - sparse_categorical_accuracy: 0.4154


135/Unknown  62s 457ms/step - loss: 1.5992 - sparse_categorical_accuracy: 0.4164


136/Unknown  63s 456ms/step - loss: 1.5963 - sparse_categorical_accuracy: 0.4175


137/Unknown  63s 456ms/step - loss: 1.5934 - sparse_categorical_accuracy: 0.4186


138/Unknown  63s 455ms/step - loss: 1.5905 - sparse_categorical_accuracy: 0.4196


139/Unknown  64s 455ms/step - loss: 1.5876 - sparse_categorical_accuracy: 0.4207


140/Unknown  64s 455ms/step - loss: 1.5848 - sparse_categorical_accuracy: 0.4217


141/Unknown  65s 455ms/step - loss: 1.5820 - sparse_categorical_accuracy: 0.4227


142/Unknown  65s 455ms/step - loss: 1.5792 - sparse_categorical_accuracy: 0.4237


143/Unknown  66s 455ms/step - loss: 1.5764 - sparse_categorical_accuracy: 0.4247


144/Unknown  66s 455ms/step - loss: 1.5737 - sparse_categorical_accuracy: 0.4257


145/Unknown  67s 455ms/step - loss: 1.5710 - sparse_categorical_accuracy: 0.4267


146/Unknown  67s 455ms/step - loss: 1.5683 - sparse_categorical_accuracy: 0.4277


147/Unknown  68s 456ms/step - loss: 1.5656 - sparse_categorical_accuracy: 0.4287


148/Unknown  68s 456ms/step - loss: 1.5629 - sparse_categorical_accuracy: 0.4297


149/Unknown  69s 456ms/step - loss: 1.5602 - sparse_categorical_accuracy: 0.4306


150/Unknown  69s 456ms/step - loss: 1.5576 - sparse_categorical_accuracy: 0.4316


151/Unknown  69s 457ms/step - loss: 1.5550 - sparse_categorical_accuracy: 0.4325


152/Unknown  70s 457ms/step - loss: 1.5524 - sparse_categorical_accuracy: 0.4335


153/Unknown  70s 457ms/step - loss: 1.5498 - sparse_categorical_accuracy: 0.4344


154/Unknown  71s 457ms/step - loss: 1.5472 - sparse_categorical_accuracy: 0.4353


155/Unknown  71s 456ms/step - loss: 1.5447 - sparse_categorical_accuracy: 0.4362


156/Unknown  72s 456ms/step - loss: 1.5421 - sparse_categorical_accuracy: 0.4371


157/Unknown  72s 455ms/step - loss: 1.5396 - sparse_categorical_accuracy: 0.4381


158/Unknown  72s 455ms/step - loss: 1.5371 - sparse_categorical_accuracy: 0.4390


159/Unknown  73s 454ms/step - loss: 1.5346 - sparse_categorical_accuracy: 0.4398


160/Unknown  73s 454ms/step - loss: 1.5322 - sparse_categorical_accuracy: 0.4407


161/Unknown  74s 454ms/step - loss: 1.5297 - sparse_categorical_accuracy: 0.4416


162/Unknown  74s 453ms/step - loss: 1.5273 - sparse_categorical_accuracy: 0.4425


163/Unknown  74s 453ms/step - loss: 1.5249 - sparse_categorical_accuracy: 0.4433


164/Unknown  75s 453ms/step - loss: 1.5225 - sparse_categorical_accuracy: 0.4442


165/Unknown  75s 453ms/step - loss: 1.5201 - sparse_categorical_accuracy: 0.4450


166/Unknown  76s 453ms/step - loss: 1.5178 - sparse_categorical_accuracy: 0.4459


167/Unknown  76s 452ms/step - loss: 1.5154 - sparse_categorical_accuracy: 0.4467


168/Unknown  77s 452ms/step - loss: 1.5131 - sparse_categorical_accuracy: 0.4475


169/Unknown  77s 452ms/step - loss: 1.5108 - sparse_categorical_accuracy: 0.4483


170/Unknown  77s 453ms/step - loss: 1.5085 - sparse_categorical_accuracy: 0.4491


171/Unknown  78s 453ms/step - loss: 1.5062 - sparse_categorical_accuracy: 0.4500


172/Unknown  78s 453ms/step - loss: 1.5039 - sparse_categorical_accuracy: 0.4508


173/Unknown  79s 453ms/step - loss: 1.5017 - sparse_categorical_accuracy: 0.4515


174/Unknown  79s 452ms/step - loss: 1.4994 - sparse_categorical_accuracy: 0.4523


175/Unknown  80s 452ms/step - loss: 1.4972 - sparse_categorical_accuracy: 0.4531


176/Unknown  80s 452ms/step - loss: 1.4950 - sparse_categorical_accuracy: 0.4539


177/Unknown  80s 451ms/step - loss: 1.4928 - sparse_categorical_accuracy: 0.4547


178/Unknown  81s 451ms/step - loss: 1.4906 - sparse_categorical_accuracy: 0.4554


179/Unknown  81s 450ms/step - loss: 1.4884 - sparse_categorical_accuracy: 0.4562


180/Unknown  82s 450ms/step - loss: 1.4863 - sparse_categorical_accuracy: 0.4570


181/Unknown  82s 450ms/step - loss: 1.4841 - sparse_categorical_accuracy: 0.4577


182/Unknown  82s 449ms/step - loss: 1.4820 - sparse_categorical_accuracy: 0.4585


183/Unknown  83s 449ms/step - loss: 1.4799 - sparse_categorical_accuracy: 0.4592


184/Unknown  83s 449ms/step - loss: 1.4778 - sparse_categorical_accuracy: 0.4599


185/Unknown  84s 449ms/step - loss: 1.4757 - sparse_categorical_accuracy: 0.4607


186/Unknown  84s 448ms/step - loss: 1.4736 - sparse_categorical_accuracy: 0.4614


187/Unknown  84s 448ms/step - loss: 1.4715 - sparse_categorical_accuracy: 0.4621


188/Unknown  85s 448ms/step - loss: 1.4695 - sparse_categorical_accuracy: 0.4628


189/Unknown  85s 448ms/step - loss: 1.4674 - sparse_categorical_accuracy: 0.4635


190/Unknown  86s 448ms/step - loss: 1.4654 - sparse_categorical_accuracy: 0.4643


191/Unknown  86s 449ms/step - loss: 1.4634 - sparse_categorical_accuracy: 0.4650


192/Unknown  87s 449ms/step - loss: 1.4614 - sparse_categorical_accuracy: 0.4656


193/Unknown  87s 449ms/step - loss: 1.4594 - sparse_categorical_accuracy: 0.4663


194/Unknown  88s 448ms/step - loss: 1.4574 - sparse_categorical_accuracy: 0.4670


195/Unknown  88s 448ms/step - loss: 1.4554 - sparse_categorical_accuracy: 0.4677


196/Unknown  88s 449ms/step - loss: 1.4535 - sparse_categorical_accuracy: 0.4684


197/Unknown  89s 449ms/step - loss: 1.4515 - sparse_categorical_accuracy: 0.4691


198/Unknown  89s 449ms/step - loss: 1.4496 - sparse_categorical_accuracy: 0.4697


199/Unknown  90s 449ms/step - loss: 1.4476 - sparse_categorical_accuracy: 0.4704


200/Unknown  90s 449ms/step - loss: 1.4457 - sparse_categorical_accuracy: 0.4711


201/Unknown  91s 449ms/step - loss: 1.4438 - sparse_categorical_accuracy: 0.4717


202/Unknown  91s 449ms/step - loss: 1.4419 - sparse_categorical_accuracy: 0.4724


203/Unknown  92s 449ms/step - loss: 1.4401 - sparse_categorical_accuracy: 0.4730


204/Unknown  92s 449ms/step - loss: 1.4382 - sparse_categorical_accuracy: 0.4737


205/Unknown  92s 448ms/step - loss: 1.4363 - sparse_categorical_accuracy: 0.4743


206/Unknown  93s 448ms/step - loss: 1.4345 - sparse_categorical_accuracy: 0.4749


207/Unknown  93s 447ms/step - loss: 1.4327 - sparse_categorical_accuracy: 0.4756


208/Unknown  94s 447ms/step - loss: 1.4308 - sparse_categorical_accuracy: 0.4762


209/Unknown  94s 447ms/step - loss: 1.4290 - sparse_categorical_accuracy: 0.4768


210/Unknown  94s 446ms/step - loss: 1.4272 - sparse_categorical_accuracy: 0.4774


211/Unknown  95s 446ms/step - loss: 1.4254 - sparse_categorical_accuracy: 0.4780


212/Unknown  95s 446ms/step - loss: 1.4237 - sparse_categorical_accuracy: 0.4786


213/Unknown  95s 446ms/step - loss: 1.4219 - sparse_categorical_accuracy: 0.4793


214/Unknown  96s 445ms/step - loss: 1.4201 - sparse_categorical_accuracy: 0.4799


215/Unknown  96s 445ms/step - loss: 1.4184 - sparse_categorical_accuracy: 0.4805


216/Unknown  97s 445ms/step - loss: 1.4166 - sparse_categorical_accuracy: 0.4811


217/Unknown  97s 445ms/step - loss: 1.4149 - sparse_categorical_accuracy: 0.4816


218/Unknown  98s 445ms/step - loss: 1.4132 - sparse_categorical_accuracy: 0.4822


219/Unknown  98s 445ms/step - loss: 1.4115 - sparse_categorical_accuracy: 0.4828


220/Unknown  98s 445ms/step - loss: 1.4098 - sparse_categorical_accuracy: 0.4834


221/Unknown  99s 445ms/step - loss: 1.4081 - sparse_categorical_accuracy: 0.4840


222/Unknown  99s 445ms/step - loss: 1.4064 - sparse_categorical_accuracy: 0.4846


223/Unknown  100s 444ms/step - loss: 1.4047 - sparse_categorical_accuracy: 0.4851


224/Unknown  100s 444ms/step - loss: 1.4030 - sparse_categorical_accuracy: 0.4857


225/Unknown  100s 444ms/step - loss: 1.4014 - sparse_categorical_accuracy: 0.4863


226/Unknown  101s 443ms/step - loss: 1.3997 - sparse_categorical_accuracy: 0.4868


227/Unknown  101s 442ms/step - loss: 1.3981 - sparse_categorical_accuracy: 0.4874


228/Unknown  101s 442ms/step - loss: 1.3965 - sparse_categorical_accuracy: 0.4879


229/Unknown  102s 441ms/step - loss: 1.3948 - sparse_categorical_accuracy: 0.4885


230/Unknown  102s 441ms/step - loss: 1.3932 - sparse_categorical_accuracy: 0.4890


231/Unknown  102s 441ms/step - loss: 1.3916 - sparse_categorical_accuracy: 0.4896


232/Unknown  103s 440ms/step - loss: 1.3900 - sparse_categorical_accuracy: 0.4901


233/Unknown  103s 440ms/step - loss: 1.3884 - sparse_categorical_accuracy: 0.4907


234/Unknown  103s 440ms/step - loss: 1.3868 - sparse_categorical_accuracy: 0.4912


235/Unknown  104s 439ms/step - loss: 1.3853 - sparse_categorical_accuracy: 0.4917


236/Unknown  104s 439ms/step - loss: 1.3837 - sparse_categorical_accuracy: 0.4923


237/Unknown  105s 439ms/step - loss: 1.3821 - sparse_categorical_accuracy: 0.4928


238/Unknown  105s 439ms/step - loss: 1.3806 - sparse_categorical_accuracy: 0.4933


239/Unknown  105s 439ms/step - loss: 1.3791 - sparse_categorical_accuracy: 0.4939


240/Unknown  106s 439ms/step - loss: 1.3775 - sparse_categorical_accuracy: 0.4944


241/Unknown  106s 439ms/step - loss: 1.3760 - sparse_categorical_accuracy: 0.4949


242/Unknown  107s 439ms/step - loss: 1.3745 - sparse_categorical_accuracy: 0.4954


243/Unknown  107s 440ms/step - loss: 1.3730 - sparse_categorical_accuracy: 0.4959


244/Unknown  108s 440ms/step - loss: 1.3715 - sparse_categorical_accuracy: 0.4964


245/Unknown  108s 440ms/step - loss: 1.3700 - sparse_categorical_accuracy: 0.4969


246/Unknown  109s 440ms/step - loss: 1.3685 - sparse_categorical_accuracy: 0.4974


247/Unknown  109s 440ms/step - loss: 1.3670 - sparse_categorical_accuracy: 0.4979


248/Unknown  110s 440ms/step - loss: 1.3655 - sparse_categorical_accuracy: 0.4984


249/Unknown  110s 440ms/step - loss: 1.3641 - sparse_categorical_accuracy: 0.4989


250/Unknown  111s 440ms/step - loss: 1.3626 - sparse_categorical_accuracy: 0.4994


251/Unknown  111s 440ms/step - loss: 1.3612 - sparse_categorical_accuracy: 0.4999


252/Unknown  111s 440ms/step - loss: 1.3597 - sparse_categorical_accuracy: 0.5004


253/Unknown  112s 440ms/step - loss: 1.3583 - sparse_categorical_accuracy: 0.5009


254/Unknown  112s 440ms/step - loss: 1.3569 - sparse_categorical_accuracy: 0.5014


255/Unknown  113s 440ms/step - loss: 1.3554 - sparse_categorical_accuracy: 0.5018


256/Unknown  113s 439ms/step - loss: 1.3540 - sparse_categorical_accuracy: 0.5023


257/Unknown  113s 439ms/step - loss: 1.3526 - sparse_categorical_accuracy: 0.5028


258/Unknown  114s 439ms/step - loss: 1.3512 - sparse_categorical_accuracy: 0.5032


259/Unknown  114s 439ms/step - loss: 1.3498 - sparse_categorical_accuracy: 0.5037


260/Unknown  115s 438ms/step - loss: 1.3484 - sparse_categorical_accuracy: 0.5042


261/Unknown  115s 438ms/step - loss: 1.3471 - sparse_categorical_accuracy: 0.5046


262/Unknown  115s 438ms/step - loss: 1.3457 - sparse_categorical_accuracy: 0.5051


263/Unknown  116s 438ms/step - loss: 1.3443 - sparse_categorical_accuracy: 0.5055


264/Unknown  116s 438ms/step - loss: 1.3430 - sparse_categorical_accuracy: 0.5060


265/Unknown  117s 438ms/step - loss: 1.3416 - sparse_categorical_accuracy: 0.5065


266/Unknown  117s 437ms/step - loss: 1.3403 - sparse_categorical_accuracy: 0.5069


267/Unknown  117s 437ms/step - loss: 1.3389 - sparse_categorical_accuracy: 0.5074


268/Unknown  118s 437ms/step - loss: 1.3376 - sparse_categorical_accuracy: 0.5078


269/Unknown  118s 438ms/step - loss: 1.3363 - sparse_categorical_accuracy: 0.5082


270/Unknown  119s 438ms/step - loss: 1.3349 - sparse_categorical_accuracy: 0.5087


271/Unknown  119s 438ms/step - loss: 1.3336 - sparse_categorical_accuracy: 0.5091


272/Unknown  120s 438ms/step - loss: 1.3323 - sparse_categorical_accuracy: 0.5096


273/Unknown  120s 438ms/step - loss: 1.3310 - sparse_categorical_accuracy: 0.5100


274/Unknown  121s 439ms/step - loss: 1.3297 - sparse_categorical_accuracy: 0.5104


275/Unknown  121s 439ms/step - loss: 1.3284 - sparse_categorical_accuracy: 0.5108


276/Unknown  122s 439ms/step - loss: 1.3271 - sparse_categorical_accuracy: 0.5113


277/Unknown  122s 439ms/step - loss: 1.3259 - sparse_categorical_accuracy: 0.5117


278/Unknown  123s 439ms/step - loss: 1.3246 - sparse_categorical_accuracy: 0.5121


279/Unknown  123s 439ms/step - loss: 1.3233 - sparse_categorical_accuracy: 0.5125


280/Unknown  123s 439ms/step - loss: 1.3221 - sparse_categorical_accuracy: 0.5130


281/Unknown  124s 439ms/step - loss: 1.3208 - sparse_categorical_accuracy: 0.5134


282/Unknown  124s 439ms/step - loss: 1.3196 - sparse_categorical_accuracy: 0.5138


283/Unknown  125s 439ms/step - loss: 1.3183 - sparse_categorical_accuracy: 0.5142


284/Unknown  125s 439ms/step - loss: 1.3171 - sparse_categorical_accuracy: 0.5146


285/Unknown  126s 439ms/step - loss: 1.3158 - sparse_categorical_accuracy: 0.5150


286/Unknown  126s 438ms/step - loss: 1.3146 - sparse_categorical_accuracy: 0.5154


287/Unknown  126s 438ms/step - loss: 1.3134 - sparse_categorical_accuracy: 0.5158


288/Unknown  127s 438ms/step - loss: 1.3122 - sparse_categorical_accuracy: 0.5162


289/Unknown  127s 438ms/step - loss: 1.3110 - sparse_categorical_accuracy: 0.5166


290/Unknown  128s 438ms/step - loss: 1.3097 - sparse_categorical_accuracy: 0.5170


291/Unknown  128s 438ms/step - loss: 1.3085 - sparse_categorical_accuracy: 0.5174


292/Unknown  128s 438ms/step - loss: 1.3073 - sparse_categorical_accuracy: 0.5178


293/Unknown  129s 437ms/step - loss: 1.3062 - sparse_categorical_accuracy: 0.5182


294/Unknown  129s 437ms/step - loss: 1.3050 - sparse_categorical_accuracy: 0.5186


295/Unknown  130s 437ms/step - loss: 1.3038 - sparse_categorical_accuracy: 0.5190


296/Unknown  130s 438ms/step - loss: 1.3026 - sparse_categorical_accuracy: 0.5194


297/Unknown  131s 438ms/step - loss: 1.3014 - sparse_categorical_accuracy: 0.5198


298/Unknown  131s 438ms/step - loss: 1.3003 - sparse_categorical_accuracy: 0.5202


299/Unknown  131s 438ms/step - loss: 1.2991 - sparse_categorical_accuracy: 0.5205


300/Unknown  132s 438ms/step - loss: 1.2980 - sparse_categorical_accuracy: 0.5209


301/Unknown  132s 438ms/step - loss: 1.2968 - sparse_categorical_accuracy: 0.5213


302/Unknown  133s 438ms/step - loss: 1.2957 - sparse_categorical_accuracy: 0.5217


303/Unknown  133s 438ms/step - loss: 1.2945 - sparse_categorical_accuracy: 0.5221


304/Unknown  134s 438ms/step - loss: 1.2934 - sparse_categorical_accuracy: 0.5224


305/Unknown  134s 438ms/step - loss: 1.2923 - sparse_categorical_accuracy: 0.5228


306/Unknown  135s 439ms/step - loss: 1.2911 - sparse_categorical_accuracy: 0.5232


307/Unknown  135s 439ms/step - loss: 1.2900 - sparse_categorical_accuracy: 0.5235


308/Unknown  136s 439ms/step - loss: 1.2889 - sparse_categorical_accuracy: 0.5239


309/Unknown  136s 439ms/step - loss: 1.2878 - sparse_categorical_accuracy: 0.5243


310/Unknown  137s 439ms/step - loss: 1.2867 - sparse_categorical_accuracy: 0.5246


311/Unknown  137s 439ms/step - loss: 1.2856 - sparse_categorical_accuracy: 0.5250


312/Unknown  137s 439ms/step - loss: 1.2845 - sparse_categorical_accuracy: 0.5254


313/Unknown  138s 439ms/step - loss: 1.2834 - sparse_categorical_accuracy: 0.5257


314/Unknown  138s 439ms/step - loss: 1.2823 - sparse_categorical_accuracy: 0.5261


315/Unknown  139s 439ms/step - loss: 1.2812 - sparse_categorical_accuracy: 0.5264


316/Unknown  139s 439ms/step - loss: 1.2801 - sparse_categorical_accuracy: 0.5268


317/Unknown  140s 439ms/step - loss: 1.2790 - sparse_categorical_accuracy: 0.5271


318/Unknown  140s 439ms/step - loss: 1.2780 - sparse_categorical_accuracy: 0.5275


319/Unknown  141s 439ms/step - loss: 1.2769 - sparse_categorical_accuracy: 0.5278


320/Unknown  141s 439ms/step - loss: 1.2758 - sparse_categorical_accuracy: 0.5282


321/Unknown  142s 439ms/step - loss: 1.2748 - sparse_categorical_accuracy: 0.5285


322/Unknown  142s 439ms/step - loss: 1.2737 - sparse_categorical_accuracy: 0.5289


323/Unknown  143s 439ms/step - loss: 1.2727 - sparse_categorical_accuracy: 0.5292


324/Unknown  143s 440ms/step - loss: 1.2716 - sparse_categorical_accuracy: 0.5296


325/Unknown  143s 440ms/step - loss: 1.2706 - sparse_categorical_accuracy: 0.5299


326/Unknown  144s 439ms/step - loss: 1.2695 - sparse_categorical_accuracy: 0.5303


327/Unknown  144s 439ms/step - loss: 1.2685 - sparse_categorical_accuracy: 0.5306


328/Unknown  145s 439ms/step - loss: 1.2675 - sparse_categorical_accuracy: 0.5309


329/Unknown  145s 439ms/step - loss: 1.2664 - sparse_categorical_accuracy: 0.5313


330/Unknown  145s 439ms/step - loss: 1.2654 - sparse_categorical_accuracy: 0.5316


331/Unknown  146s 438ms/step - loss: 1.2644 - sparse_categorical_accuracy: 0.5319


332/Unknown  146s 438ms/step - loss: 1.2634 - sparse_categorical_accuracy: 0.5323


333/Unknown  147s 438ms/step - loss: 1.2624 - sparse_categorical_accuracy: 0.5326


334/Unknown  147s 438ms/step - loss: 1.2614 - sparse_categorical_accuracy: 0.5329


335/Unknown  147s 438ms/step - loss: 1.2604 - sparse_categorical_accuracy: 0.5333


336/Unknown  148s 438ms/step - loss: 1.2594 - sparse_categorical_accuracy: 0.5336


337/Unknown  148s 438ms/step - loss: 1.2584 - sparse_categorical_accuracy: 0.5339


338/Unknown  148s 438ms/step - loss: 1.2574 - sparse_categorical_accuracy: 0.5342


339/Unknown  149s 438ms/step - loss: 1.2564 - sparse_categorical_accuracy: 0.5345


340/Unknown  149s 438ms/step - loss: 1.2554 - sparse_categorical_accuracy: 0.5349


341/Unknown  150s 438ms/step - loss: 1.2545 - sparse_categorical_accuracy: 0.5352


342/Unknown  150s 438ms/step - loss: 1.2535 - sparse_categorical_accuracy: 0.5355


343/Unknown  151s 438ms/step - loss: 1.2525 - sparse_categorical_accuracy: 0.5358


344/Unknown  151s 438ms/step - loss: 1.2515 - sparse_categorical_accuracy: 0.5361


345/Unknown  152s 438ms/step - loss: 1.2506 - sparse_categorical_accuracy: 0.5364


346/Unknown  152s 439ms/step - loss: 1.2496 - sparse_categorical_accuracy: 0.5368


347/Unknown  153s 439ms/step - loss: 1.2487 - sparse_categorical_accuracy: 0.5371


348/Unknown  153s 439ms/step - loss: 1.2477 - sparse_categorical_accuracy: 0.5374


349/Unknown  154s 439ms/step - loss: 1.2468 - sparse_categorical_accuracy: 0.5377


350/Unknown  154s 439ms/step - loss: 1.2458 - sparse_categorical_accuracy: 0.5380


351/Unknown  154s 438ms/step - loss: 1.2449 - sparse_categorical_accuracy: 0.5383


352/Unknown  155s 439ms/step - loss: 1.2439 - sparse_categorical_accuracy: 0.5386


353/Unknown  155s 439ms/step - loss: 1.2430 - sparse_categorical_accuracy: 0.5389


354/Unknown  156s 439ms/step - loss: 1.2421 - sparse_categorical_accuracy: 0.5392


355/Unknown  156s 439ms/step - loss: 1.2412 - sparse_categorical_accuracy: 0.5395


356/Unknown  157s 439ms/step - loss: 1.2402 - sparse_categorical_accuracy: 0.5398


357/Unknown  157s 439ms/step - loss: 1.2393 - sparse_categorical_accuracy: 0.5401


358/Unknown  158s 439ms/step - loss: 1.2384 - sparse_categorical_accuracy: 0.5404


359/Unknown  158s 439ms/step - loss: 1.2375 - sparse_categorical_accuracy: 0.5407


360/Unknown  159s 439ms/step - loss: 1.2366 - sparse_categorical_accuracy: 0.5410


361/Unknown  159s 439ms/step - loss: 1.2357 - sparse_categorical_accuracy: 0.5413


362/Unknown  160s 440ms/step - loss: 1.2348 - sparse_categorical_accuracy: 0.5416


363/Unknown  160s 440ms/step - loss: 1.2339 - sparse_categorical_accuracy: 0.5419


364/Unknown  161s 440ms/step - loss: 1.2330 - sparse_categorical_accuracy: 0.5421


365/Unknown  161s 440ms/step - loss: 1.2321 - sparse_categorical_accuracy: 0.5424


366/Unknown  162s 440ms/step - loss: 1.2312 - sparse_categorical_accuracy: 0.5427


367/Unknown  162s 441ms/step - loss: 1.2303 - sparse_categorical_accuracy: 0.5430


368/Unknown  163s 441ms/step - loss: 1.2294 - sparse_categorical_accuracy: 0.5433


369/Unknown  163s 441ms/step - loss: 1.2285 - sparse_categorical_accuracy: 0.5436


370/Unknown  164s 441ms/step - loss: 1.2277 - sparse_categorical_accuracy: 0.5439


371/Unknown  164s 441ms/step - loss: 1.2268 - sparse_categorical_accuracy: 0.5441


372/Unknown  165s 441ms/step - loss: 1.2259 - sparse_categorical_accuracy: 0.5444


373/Unknown  165s 441ms/step - loss: 1.2251 - sparse_categorical_accuracy: 0.5447


374/Unknown  165s 441ms/step - loss: 1.2242 - sparse_categorical_accuracy: 0.5450


375/Unknown  166s 441ms/step - loss: 1.2233 - sparse_categorical_accuracy: 0.5453


376/Unknown  166s 441ms/step - loss: 1.2225 - sparse_categorical_accuracy: 0.5455


377/Unknown  167s 440ms/step - loss: 1.2216 - sparse_categorical_accuracy: 0.5458


378/Unknown  167s 440ms/step - loss: 1.2208 - sparse_categorical_accuracy: 0.5461


379/Unknown  167s 440ms/step - loss: 1.2199 - sparse_categorical_accuracy: 0.5464


380/Unknown  168s 440ms/step - loss: 1.2191 - sparse_categorical_accuracy: 0.5466


381/Unknown  168s 440ms/step - loss: 1.2182 - sparse_categorical_accuracy: 0.5469


382/Unknown  169s 440ms/step - loss: 1.2174 - sparse_categorical_accuracy: 0.5472


383/Unknown  169s 440ms/step - loss: 1.2165 - sparse_categorical_accuracy: 0.5475


384/Unknown  169s 440ms/step - loss: 1.2157 - sparse_categorical_accuracy: 0.5477


385/Unknown  170s 439ms/step - loss: 1.2149 - sparse_categorical_accuracy: 0.5480


386/Unknown  170s 440ms/step - loss: 1.2140 - sparse_categorical_accuracy: 0.5483


387/Unknown  171s 440ms/step - loss: 1.2132 - sparse_categorical_accuracy: 0.5485


388/Unknown  171s 440ms/step - loss: 1.2124 - sparse_categorical_accuracy: 0.5488


389/Unknown  172s 440ms/step - loss: 1.2116 - sparse_categorical_accuracy: 0.5491


390/Unknown  172s 440ms/step - loss: 1.2108 - sparse_categorical_accuracy: 0.5493


391/Unknown  173s 440ms/step - loss: 1.2099 - sparse_categorical_accuracy: 0.5496


392/Unknown  173s 440ms/step - loss: 1.2091 - sparse_categorical_accuracy: 0.5499


393/Unknown  174s 440ms/step - loss: 1.2083 - sparse_categorical_accuracy: 0.5501


394/Unknown  174s 440ms/step - loss: 1.2075 - sparse_categorical_accuracy: 0.5504


395/Unknown  175s 440ms/step - loss: 1.2067 - sparse_categorical_accuracy: 0.5506


396/Unknown  175s 441ms/step - loss: 1.2059 - sparse_categorical_accuracy: 0.5509


397/Unknown  175s 441ms/step - loss: 1.2051 - sparse_categorical_accuracy: 0.5512


398/Unknown  176s 440ms/step - loss: 1.2043 - sparse_categorical_accuracy: 0.5514


399/Unknown  176s 440ms/step - loss: 1.2035 - sparse_categorical_accuracy: 0.5517


400/Unknown  177s 440ms/step - loss: 1.2027 - sparse_categorical_accuracy: 0.5519


401/Unknown  177s 441ms/step - loss: 1.2019 - sparse_categorical_accuracy: 0.5522


402/Unknown  178s 441ms/step - loss: 1.2011 - sparse_categorical_accuracy: 0.5524


403/Unknown  178s 441ms/step - loss: 1.2004 - sparse_categorical_accuracy: 0.5527


404/Unknown  179s 441ms/step - loss: 1.1996 - sparse_categorical_accuracy: 0.5529


405/Unknown  179s 441ms/step - loss: 1.1988 - sparse_categorical_accuracy: 0.5532


406/Unknown  180s 441ms/step - loss: 1.1980 - sparse_categorical_accuracy: 0.5534


407/Unknown  180s 441ms/step - loss: 1.1973 - sparse_categorical_accuracy: 0.5537


408/Unknown  181s 441ms/step - loss: 1.1965 - sparse_categorical_accuracy: 0.5539


409/Unknown  181s 442ms/step - loss: 1.1957 - sparse_categorical_accuracy: 0.5542


410/Unknown  182s 442ms/step - loss: 1.1950 - sparse_categorical_accuracy: 0.5544


411/Unknown  182s 442ms/step - loss: 1.1942 - sparse_categorical_accuracy: 0.5547


412/Unknown  183s 442ms/step - loss: 1.1934 - sparse_categorical_accuracy: 0.5549


413/Unknown  183s 442ms/step - loss: 1.1927 - sparse_categorical_accuracy: 0.5552


414/Unknown  184s 442ms/step - loss: 1.1919 - sparse_categorical_accuracy: 0.5554


415/Unknown  184s 442ms/step - loss: 1.1912 - sparse_categorical_accuracy: 0.5556


416/Unknown  185s 442ms/step - loss: 1.1904 - sparse_categorical_accuracy: 0.5559


417/Unknown  185s 443ms/step - loss: 1.1897 - sparse_categorical_accuracy: 0.5561


418/Unknown  186s 443ms/step - loss: 1.1890 - sparse_categorical_accuracy: 0.5564


419/Unknown  186s 443ms/step - loss: 1.1882 - sparse_categorical_accuracy: 0.5566


420/Unknown  187s 443ms/step - loss: 1.1875 - sparse_categorical_accuracy: 0.5568


421/Unknown  187s 443ms/step - loss: 1.1867 - sparse_categorical_accuracy: 0.5571


422/Unknown  187s 443ms/step - loss: 1.1860 - sparse_categorical_accuracy: 0.5573


423/Unknown  188s 443ms/step - loss: 1.1853 - sparse_categorical_accuracy: 0.5575


424/Unknown  188s 443ms/step - loss: 1.1846 - sparse_categorical_accuracy: 0.5578


425/Unknown  189s 443ms/step - loss: 1.1838 - sparse_categorical_accuracy: 0.5580


426/Unknown  190s 444ms/step - loss: 1.1831 - sparse_categorical_accuracy: 0.5582


427/Unknown  190s 444ms/step - loss: 1.1824 - sparse_categorical_accuracy: 0.5585


428/Unknown  190s 444ms/step - loss: 1.1817 - sparse_categorical_accuracy: 0.5587


429/Unknown  191s 444ms/step - loss: 1.1810 - sparse_categorical_accuracy: 0.5589


430/Unknown  191s 444ms/step - loss: 1.1802 - sparse_categorical_accuracy: 0.5592


431/Unknown  192s 444ms/step - loss: 1.1795 - sparse_categorical_accuracy: 0.5594


432/Unknown  192s 444ms/step - loss: 1.1788 - sparse_categorical_accuracy: 0.5596


433/Unknown  193s 444ms/step - loss: 1.1781 - sparse_categorical_accuracy: 0.5599


434/Unknown  193s 444ms/step - loss: 1.1774 - sparse_categorical_accuracy: 0.5601


435/Unknown  195s 446ms/step - loss: 1.1767 - sparse_categorical_accuracy: 0.5603


436/Unknown  195s 447ms/step - loss: 1.1760 - sparse_categorical_accuracy: 0.5605


437/Unknown  196s 447ms/step - loss: 1.1753 - sparse_categorical_accuracy: 0.5608


438/Unknown  196s 447ms/step - loss: 1.1746 - sparse_categorical_accuracy: 0.5610


439/Unknown  197s 447ms/step - loss: 1.1739 - sparse_categorical_accuracy: 0.5612


440/Unknown  197s 447ms/step - loss: 1.1732 - sparse_categorical_accuracy: 0.5614


441/Unknown  198s 447ms/step - loss: 1.1726 - sparse_categorical_accuracy: 0.5616


442/Unknown  198s 447ms/step - loss: 1.1719 - sparse_categorical_accuracy: 0.5619


443/Unknown  199s 447ms/step - loss: 1.1712 - sparse_categorical_accuracy: 0.5621


444/Unknown  199s 447ms/step - loss: 1.1705 - sparse_categorical_accuracy: 0.5623


445/Unknown  199s 447ms/step - loss: 1.1698 - sparse_categorical_accuracy: 0.5625


446/Unknown  200s 447ms/step - loss: 1.1691 - sparse_categorical_accuracy: 0.5627


447/Unknown  200s 447ms/step - loss: 1.1685 - sparse_categorical_accuracy: 0.5629


448/Unknown  201s 447ms/step - loss: 1.1678 - sparse_categorical_accuracy: 0.5632


449/Unknown  201s 447ms/step - loss: 1.1671 - sparse_categorical_accuracy: 0.5634


450/Unknown  202s 447ms/step - loss: 1.1665 - sparse_categorical_accuracy: 0.5636


451/Unknown  202s 447ms/step - loss: 1.1658 - sparse_categorical_accuracy: 0.5638


452/Unknown  203s 448ms/step - loss: 1.1651 - sparse_categorical_accuracy: 0.5640


453/Unknown  203s 448ms/step - loss: 1.1645 - sparse_categorical_accuracy: 0.5642


454/Unknown  204s 448ms/step - loss: 1.1638 - sparse_categorical_accuracy: 0.5644


455/Unknown  204s 448ms/step - loss: 1.1631 - sparse_categorical_accuracy: 0.5647


456/Unknown  205s 448ms/step - loss: 1.1625 - sparse_categorical_accuracy: 0.5649


457/Unknown  205s 448ms/step - loss: 1.1618 - sparse_categorical_accuracy: 0.5651


458/Unknown  206s 448ms/step - loss: 1.1612 - sparse_categorical_accuracy: 0.5653


459/Unknown  206s 448ms/step - loss: 1.1605 - sparse_categorical_accuracy: 0.5655


460/Unknown  207s 448ms/step - loss: 1.1599 - sparse_categorical_accuracy: 0.5657


461/Unknown  207s 448ms/step - loss: 1.1592 - sparse_categorical_accuracy: 0.5659


462/Unknown  208s 448ms/step - loss: 1.1586 - sparse_categorical_accuracy: 0.5661


463/Unknown  208s 448ms/step - loss: 1.1579 - sparse_categorical_accuracy: 0.5663


464/Unknown  209s 448ms/step - loss: 1.1573 - sparse_categorical_accuracy: 0.5665


465/Unknown  209s 448ms/step - loss: 1.1566 - sparse_categorical_accuracy: 0.5667


466/Unknown  210s 448ms/step - loss: 1.1560 - sparse_categorical_accuracy: 0.5669


467/Unknown  210s 449ms/step - loss: 1.1554 - sparse_categorical_accuracy: 0.5671


468/Unknown  211s 449ms/step - loss: 1.1547 - sparse_categorical_accuracy: 0.5674


469/Unknown  211s 449ms/step - loss: 1.1541 - sparse_categorical_accuracy: 0.5676


470/Unknown  212s 449ms/step - loss: 1.1535 - sparse_categorical_accuracy: 0.5678


471/Unknown  212s 449ms/step - loss: 1.1528 - sparse_categorical_accuracy: 0.5680


472/Unknown  212s 449ms/step - loss: 1.1522 - sparse_categorical_accuracy: 0.5682


473/Unknown  213s 449ms/step - loss: 1.1516 - sparse_categorical_accuracy: 0.5684


474/Unknown  213s 449ms/step - loss: 1.1510 - sparse_categorical_accuracy: 0.5686


475/Unknown  214s 449ms/step - loss: 1.1503 - sparse_categorical_accuracy: 0.5688


476/Unknown  214s 449ms/step - loss: 1.1497 - sparse_categorical_accuracy: 0.5690


477/Unknown  215s 449ms/step - loss: 1.1491 - sparse_categorical_accuracy: 0.5692


478/Unknown  215s 449ms/step - loss: 1.1485 - sparse_categorical_accuracy: 0.5694


479/Unknown  216s 449ms/step - loss: 1.1479 - sparse_categorical_accuracy: 0.5695


480/Unknown  216s 450ms/step - loss: 1.1473 - sparse_categorical_accuracy: 0.5697


481/Unknown  217s 450ms/step - loss: 1.1466 - sparse_categorical_accuracy: 0.5699


482/Unknown  217s 450ms/step - loss: 1.1460 - sparse_categorical_accuracy: 0.5701


483/Unknown  218s 450ms/step - loss: 1.1454 - sparse_categorical_accuracy: 0.5703


484/Unknown  218s 450ms/step - loss: 1.1448 - sparse_categorical_accuracy: 0.5705


485/Unknown  219s 450ms/step - loss: 1.1442 - sparse_categorical_accuracy: 0.5707


486/Unknown  219s 450ms/step - loss: 1.1436 - sparse_categorical_accuracy: 0.5709


487/Unknown  220s 450ms/step - loss: 1.1430 - sparse_categorical_accuracy: 0.5711


488/Unknown  220s 450ms/step - loss: 1.1424 - sparse_categorical_accuracy: 0.5713


489/Unknown  221s 450ms/step - loss: 1.1418 - sparse_categorical_accuracy: 0.5715


490/Unknown  221s 450ms/step - loss: 1.1412 - sparse_categorical_accuracy: 0.5717


491/Unknown  222s 450ms/step - loss: 1.1406 - sparse_categorical_accuracy: 0.5719


492/Unknown  222s 450ms/step - loss: 1.1400 - sparse_categorical_accuracy: 0.5720


493/Unknown  223s 450ms/step - loss: 1.1394 - sparse_categorical_accuracy: 0.5722


494/Unknown  223s 451ms/step - loss: 1.1389 - sparse_categorical_accuracy: 0.5724


495/Unknown  224s 451ms/step - loss: 1.1383 - sparse_categorical_accuracy: 0.5726


496/Unknown  224s 451ms/step - loss: 1.1377 - sparse_categorical_accuracy: 0.5728


497/Unknown  225s 451ms/step - loss: 1.1371 - sparse_categorical_accuracy: 0.5730


498/Unknown  225s 451ms/step - loss: 1.1365 - sparse_categorical_accuracy: 0.5732


499/Unknown  226s 451ms/step - loss: 1.1359 - sparse_categorical_accuracy: 0.5734


500/Unknown  226s 451ms/step - loss: 1.1354 - sparse_categorical_accuracy: 0.5735


501/Unknown  227s 451ms/step - loss: 1.1348 - sparse_categorical_accuracy: 0.5737


502/Unknown  227s 451ms/step - loss: 1.1342 - sparse_categorical_accuracy: 0.5739


503/Unknown  228s 451ms/step - loss: 1.1336 - sparse_categorical_accuracy: 0.5741


504/Unknown  228s 451ms/step - loss: 1.1330 - sparse_categorical_accuracy: 0.5743


505/Unknown  229s 452ms/step - loss: 1.1325 - sparse_categorical_accuracy: 0.5745


506/Unknown  229s 452ms/step - loss: 1.1319 - sparse_categorical_accuracy: 0.5746


507/Unknown  230s 452ms/step - loss: 1.1313 - sparse_categorical_accuracy: 0.5748


508/Unknown  230s 452ms/step - loss: 1.1308 - sparse_categorical_accuracy: 0.5750


509/Unknown  230s 451ms/step - loss: 1.1302 - sparse_categorical_accuracy: 0.5752


510/Unknown  231s 452ms/step - loss: 1.1296 - sparse_categorical_accuracy: 0.5754


511/Unknown  231s 452ms/step - loss: 1.1291 - sparse_categorical_accuracy: 0.5755


512/Unknown  232s 452ms/step - loss: 1.1285 - sparse_categorical_accuracy: 0.5757


513/Unknown  232s 452ms/step - loss: 1.1280 - sparse_categorical_accuracy: 0.5759


514/Unknown  233s 452ms/step - loss: 1.1274 - sparse_categorical_accuracy: 0.5761


515/Unknown  233s 452ms/step - loss: 1.1268 - sparse_categorical_accuracy: 0.5762


516/Unknown  234s 452ms/step - loss: 1.1263 - sparse_categorical_accuracy: 0.5764


517/Unknown  234s 452ms/step - loss: 1.1257 - sparse_categorical_accuracy: 0.5766


518/Unknown  235s 452ms/step - loss: 1.1252 - sparse_categorical_accuracy: 0.5768


519/Unknown  235s 452ms/step - loss: 1.1246 - sparse_categorical_accuracy: 0.5769


520/Unknown  236s 452ms/step - loss: 1.1241 - sparse_categorical_accuracy: 0.5771


521/Unknown  236s 452ms/step - loss: 1.1236 - sparse_categorical_accuracy: 0.5773


522/Unknown  237s 452ms/step - loss: 1.1230 - sparse_categorical_accuracy: 0.5775


523/Unknown  237s 452ms/step - loss: 1.1225 - sparse_categorical_accuracy: 0.5776


524/Unknown  238s 452ms/step - loss: 1.1219 - sparse_categorical_accuracy: 0.5778


525/Unknown  238s 452ms/step - loss: 1.1214 - sparse_categorical_accuracy: 0.5780


526/Unknown  239s 453ms/step - loss: 1.1208 - sparse_categorical_accuracy: 0.5782


527/Unknown  239s 453ms/step - loss: 1.1203 - sparse_categorical_accuracy: 0.5783


528/Unknown  240s 453ms/step - loss: 1.1198 - sparse_categorical_accuracy: 0.5785


529/Unknown  240s 453ms/step - loss: 1.1192 - sparse_categorical_accuracy: 0.5787


530/Unknown  241s 453ms/step - loss: 1.1187 - sparse_categorical_accuracy: 0.5788


531/Unknown  241s 453ms/step - loss: 1.1182 - sparse_categorical_accuracy: 0.5790


532/Unknown  242s 453ms/step - loss: 1.1176 - sparse_categorical_accuracy: 0.5792


533/Unknown  242s 453ms/step - loss: 1.1171 - sparse_categorical_accuracy: 0.5793


534/Unknown  243s 453ms/step - loss: 1.1166 - sparse_categorical_accuracy: 0.5795


535/Unknown  243s 453ms/step - loss: 1.1161 - sparse_categorical_accuracy: 0.5797


536/Unknown  244s 453ms/step - loss: 1.1155 - sparse_categorical_accuracy: 0.5798


537/Unknown  244s 453ms/step - loss: 1.1150 - sparse_categorical_accuracy: 0.5800


538/Unknown  245s 454ms/step - loss: 1.1145 - sparse_categorical_accuracy: 0.5802


539/Unknown  245s 454ms/step - loss: 1.1140 - sparse_categorical_accuracy: 0.5803


540/Unknown  245s 454ms/step - loss: 1.1135 - sparse_categorical_accuracy: 0.5805


541/Unknown  246s 454ms/step - loss: 1.1129 - sparse_categorical_accuracy: 0.5807


542/Unknown  246s 454ms/step - loss: 1.1124 - sparse_categorical_accuracy: 0.5808


543/Unknown  247s 454ms/step - loss: 1.1119 - sparse_categorical_accuracy: 0.5810


544/Unknown  247s 454ms/step - loss: 1.1114 - sparse_categorical_accuracy: 0.5811


545/Unknown  248s 454ms/step - loss: 1.1109 - sparse_categorical_accuracy: 0.5813


546/Unknown  248s 454ms/step - loss: 1.1104 - sparse_categorical_accuracy: 0.5815


547/Unknown  249s 454ms/step - loss: 1.1099 - sparse_categorical_accuracy: 0.5816


548/Unknown  249s 454ms/step - loss: 1.1093 - sparse_categorical_accuracy: 0.5818


549/Unknown  250s 454ms/step - loss: 1.1088 - sparse_categorical_accuracy: 0.5820


550/Unknown  250s 454ms/step - loss: 1.1083 - sparse_categorical_accuracy: 0.5821


551/Unknown  251s 454ms/step - loss: 1.1078 - sparse_categorical_accuracy: 0.5823


552/Unknown  251s 454ms/step - loss: 1.1073 - sparse_categorical_accuracy: 0.5824


553/Unknown  252s 454ms/step - loss: 1.1068 - sparse_categorical_accuracy: 0.5826


554/Unknown  252s 454ms/step - loss: 1.1063 - sparse_categorical_accuracy: 0.5828


555/Unknown  253s 454ms/step - loss: 1.1058 - sparse_categorical_accuracy: 0.5829


556/Unknown  253s 454ms/step - loss: 1.1053 - sparse_categorical_accuracy: 0.5831


557/Unknown  254s 454ms/step - loss: 1.1048 - sparse_categorical_accuracy: 0.5832


558/Unknown  254s 455ms/step - loss: 1.1043 - sparse_categorical_accuracy: 0.5834


559/Unknown  255s 455ms/step - loss: 1.1038 - sparse_categorical_accuracy: 0.5835


560/Unknown  255s 455ms/step - loss: 1.1033 - sparse_categorical_accuracy: 0.5837


561/Unknown  256s 455ms/step - loss: 1.1029 - sparse_categorical_accuracy: 0.5839


562/Unknown  256s 455ms/step - loss: 1.1024 - sparse_categorical_accuracy: 0.5840


563/Unknown  257s 455ms/step - loss: 1.1019 - sparse_categorical_accuracy: 0.5842


564/Unknown  257s 455ms/step - loss: 1.1014 - sparse_categorical_accuracy: 0.5843


565/Unknown  257s 455ms/step - loss: 1.1009 - sparse_categorical_accuracy: 0.5845


566/Unknown  258s 455ms/step - loss: 1.1004 - sparse_categorical_accuracy: 0.5846


567/Unknown  258s 455ms/step - loss: 1.0999 - sparse_categorical_accuracy: 0.5848


568/Unknown  259s 455ms/step - loss: 1.0994 - sparse_categorical_accuracy: 0.5849


569/Unknown  259s 455ms/step - loss: 1.0990 - sparse_categorical_accuracy: 0.5851


570/Unknown  260s 455ms/step - loss: 1.0985 - sparse_categorical_accuracy: 0.5852


571/Unknown  260s 455ms/step - loss: 1.0980 - sparse_categorical_accuracy: 0.5854


572/Unknown  261s 455ms/step - loss: 1.0975 - sparse_categorical_accuracy: 0.5855


573/Unknown  261s 455ms/step - loss: 1.0970 - sparse_categorical_accuracy: 0.5857


574/Unknown  262s 455ms/step - loss: 1.0966 - sparse_categorical_accuracy: 0.5859


575/Unknown  262s 455ms/step - loss: 1.0961 - sparse_categorical_accuracy: 0.5860


576/Unknown  263s 455ms/step - loss: 1.0956 - sparse_categorical_accuracy: 0.5862


577/Unknown  263s 455ms/step - loss: 1.0951 - sparse_categorical_accuracy: 0.5863


578/Unknown  264s 455ms/step - loss: 1.0947 - sparse_categorical_accuracy: 0.5865


579/Unknown  264s 455ms/step - loss: 1.0942 - sparse_categorical_accuracy: 0.5866


580/Unknown  265s 456ms/step - loss: 1.0937 - sparse_categorical_accuracy: 0.5868


581/Unknown  265s 456ms/step - loss: 1.0933 - sparse_categorical_accuracy: 0.5869


582/Unknown  266s 456ms/step - loss: 1.0928 - sparse_categorical_accuracy: 0.5870


583/Unknown  266s 456ms/step - loss: 1.0923 - sparse_categorical_accuracy: 0.5872


584/Unknown  267s 456ms/step - loss: 1.0919 - sparse_categorical_accuracy: 0.5873


585/Unknown  267s 456ms/step - loss: 1.0914 - sparse_categorical_accuracy: 0.5875


586/Unknown  268s 456ms/step - loss: 1.0909 - sparse_categorical_accuracy: 0.5876


587/Unknown  268s 456ms/step - loss: 1.0905 - sparse_categorical_accuracy: 0.5878


588/Unknown  269s 456ms/step - loss: 1.0900 - sparse_categorical_accuracy: 0.5879


589/Unknown  269s 456ms/step - loss: 1.0896 - sparse_categorical_accuracy: 0.5881


590/Unknown  270s 456ms/step - loss: 1.0891 - sparse_categorical_accuracy: 0.5882


591/Unknown  270s 456ms/step - loss: 1.0886 - sparse_categorical_accuracy: 0.5884


592/Unknown  271s 456ms/step - loss: 1.0882 - sparse_categorical_accuracy: 0.5885


593/Unknown  271s 456ms/step - loss: 1.0877 - sparse_categorical_accuracy: 0.5887


594/Unknown  271s 456ms/step - loss: 1.0873 - sparse_categorical_accuracy: 0.5888


595/Unknown  272s 456ms/step - loss: 1.0868 - sparse_categorical_accuracy: 0.5889


596/Unknown  272s 456ms/step - loss: 1.0864 - sparse_categorical_accuracy: 0.5891


597/Unknown  273s 456ms/step - loss: 1.0859 - sparse_categorical_accuracy: 0.5892


598/Unknown  273s 456ms/step - loss: 1.0855 - sparse_categorical_accuracy: 0.5894


599/Unknown  274s 456ms/step - loss: 1.0850 - sparse_categorical_accuracy: 0.5895


600/Unknown  274s 456ms/step - loss: 1.0846 - sparse_categorical_accuracy: 0.5897


601/Unknown  275s 456ms/step - loss: 1.0841 - sparse_categorical_accuracy: 0.5898


602/Unknown  275s 456ms/step - loss: 1.0837 - sparse_categorical_accuracy: 0.5899


603/Unknown  276s 456ms/step - loss: 1.0832 - sparse_categorical_accuracy: 0.5901


604/Unknown  276s 456ms/step - loss: 1.0828 - sparse_categorical_accuracy: 0.5902


605/Unknown  277s 456ms/step - loss: 1.0824 - sparse_categorical_accuracy: 0.5904


606/Unknown  277s 457ms/step - loss: 1.0819 - sparse_categorical_accuracy: 0.5905


607/Unknown  278s 457ms/step - loss: 1.0815 - sparse_categorical_accuracy: 0.5906


608/Unknown  278s 457ms/step - loss: 1.0810 - sparse_categorical_accuracy: 0.5908


609/Unknown  279s 457ms/step - loss: 1.0806 - sparse_categorical_accuracy: 0.5909


610/Unknown  279s 457ms/step - loss: 1.0802 - sparse_categorical_accuracy: 0.5911


611/Unknown  280s 457ms/step - loss: 1.0797 - sparse_categorical_accuracy: 0.5912


612/Unknown  280s 457ms/step - loss: 1.0793 - sparse_categorical_accuracy: 0.5913


613/Unknown  280s 457ms/step - loss: 1.0789 - sparse_categorical_accuracy: 0.5915


614/Unknown  282s 458ms/step - loss: 1.0784 - sparse_categorical_accuracy: 0.5916


615/Unknown  282s 458ms/step - loss: 1.0780 - sparse_categorical_accuracy: 0.5917


616/Unknown  283s 458ms/step - loss: 1.0776 - sparse_categorical_accuracy: 0.5919


617/Unknown  283s 458ms/step - loss: 1.0771 - sparse_categorical_accuracy: 0.5920


618/Unknown  284s 458ms/step - loss: 1.0767 - sparse_categorical_accuracy: 0.5921


619/Unknown  284s 458ms/step - loss: 1.0763 - sparse_categorical_accuracy: 0.5923


620/Unknown  285s 459ms/step - loss: 1.0759 - sparse_categorical_accuracy: 0.5924


621/Unknown  285s 459ms/step - loss: 1.0754 - sparse_categorical_accuracy: 0.5926


622/Unknown  286s 459ms/step - loss: 1.0750 - sparse_categorical_accuracy: 0.5927


623/Unknown  286s 459ms/step - loss: 1.0746 - sparse_categorical_accuracy: 0.5928


624/Unknown  287s 459ms/step - loss: 1.0742 - sparse_categorical_accuracy: 0.5930


625/Unknown  287s 459ms/step - loss: 1.0737 - sparse_categorical_accuracy: 0.5931


626/Unknown  288s 459ms/step - loss: 1.0733 - sparse_categorical_accuracy: 0.5932


627/Unknown  288s 459ms/step - loss: 1.0729 - sparse_categorical_accuracy: 0.5934


628/Unknown  289s 459ms/step - loss: 1.0725 - sparse_categorical_accuracy: 0.5935


629/Unknown  289s 459ms/step - loss: 1.0721 - sparse_categorical_accuracy: 0.5936


630/Unknown  290s 459ms/step - loss: 1.0716 - sparse_categorical_accuracy: 0.5937


631/Unknown  290s 459ms/step - loss: 1.0712 - sparse_categorical_accuracy: 0.5939


632/Unknown  291s 459ms/step - loss: 1.0708 - sparse_categorical_accuracy: 0.5940


633/Unknown  291s 459ms/step - loss: 1.0704 - sparse_categorical_accuracy: 0.5941


634/Unknown  292s 459ms/step - loss: 1.0700 - sparse_categorical_accuracy: 0.5943


635/Unknown  292s 459ms/step - loss: 1.0696 - sparse_categorical_accuracy: 0.5944


636/Unknown  293s 459ms/step - loss: 1.0692 - sparse_categorical_accuracy: 0.5945


637/Unknown  293s 459ms/step - loss: 1.0688 - sparse_categorical_accuracy: 0.5947


638/Unknown  294s 459ms/step - loss: 1.0683 - sparse_categorical_accuracy: 0.5948


639/Unknown  294s 459ms/step - loss: 1.0679 - sparse_categorical_accuracy: 0.5949


640/Unknown  295s 459ms/step - loss: 1.0675 - sparse_categorical_accuracy: 0.5950


641/Unknown  295s 459ms/step - loss: 1.0671 - sparse_categorical_accuracy: 0.5952


642/Unknown  296s 460ms/step - loss: 1.0667 - sparse_categorical_accuracy: 0.5953


643/Unknown  296s 460ms/step - loss: 1.0663 - sparse_categorical_accuracy: 0.5954


644/Unknown  297s 460ms/step - loss: 1.0659 - sparse_categorical_accuracy: 0.5956


645/Unknown  297s 460ms/step - loss: 1.0655 - sparse_categorical_accuracy: 0.5957


646/Unknown  297s 460ms/step - loss: 1.0651 - sparse_categorical_accuracy: 0.5958


647/Unknown  298s 460ms/step - loss: 1.0647 - sparse_categorical_accuracy: 0.5959


648/Unknown  299s 460ms/step - loss: 1.0643 - sparse_categorical_accuracy: 0.5961


649/Unknown  299s 460ms/step - loss: 1.0639 - sparse_categorical_accuracy: 0.5962


650/Unknown  299s 460ms/step - loss: 1.0635 - sparse_categorical_accuracy: 0.5963


651/Unknown  300s 460ms/step - loss: 1.0631 - sparse_categorical_accuracy: 0.5964


652/Unknown  300s 460ms/step - loss: 1.0627 - sparse_categorical_accuracy: 0.5966


653/Unknown  301s 460ms/step - loss: 1.0623 - sparse_categorical_accuracy: 0.5967


654/Unknown  301s 460ms/step - loss: 1.0619 - sparse_categorical_accuracy: 0.5968


655/Unknown  302s 460ms/step - loss: 1.0615 - sparse_categorical_accuracy: 0.5969


656/Unknown  302s 460ms/step - loss: 1.0611 - sparse_categorical_accuracy: 0.5971


657/Unknown  303s 460ms/step - loss: 1.0608 - sparse_categorical_accuracy: 0.5972


658/Unknown  303s 460ms/step - loss: 1.0604 - sparse_categorical_accuracy: 0.5973


659/Unknown  304s 460ms/step - loss: 1.0600 - sparse_categorical_accuracy: 0.5974


660/Unknown  304s 460ms/step - loss: 1.0596 - sparse_categorical_accuracy: 0.5976


661/Unknown  305s 460ms/step - loss: 1.0592 - sparse_categorical_accuracy: 0.5977


662/Unknown  305s 460ms/step - loss: 1.0588 - sparse_categorical_accuracy: 0.5978


663/Unknown  306s 460ms/step - loss: 1.0584 - sparse_categorical_accuracy: 0.5979


664/Unknown  306s 460ms/step - loss: 1.0580 - sparse_categorical_accuracy: 0.5980


665/Unknown  306s 460ms/step - loss: 1.0577 - sparse_categorical_accuracy: 0.5982


666/Unknown  307s 460ms/step - loss: 1.0573 - sparse_categorical_accuracy: 0.5983


667/Unknown  307s 460ms/step - loss: 1.0569 - sparse_categorical_accuracy: 0.5984


668/Unknown  308s 460ms/step - loss: 1.0565 - sparse_categorical_accuracy: 0.5985


669/Unknown  308s 460ms/step - loss: 1.0561 - sparse_categorical_accuracy: 0.5986


670/Unknown  309s 460ms/step - loss: 1.0557 - sparse_categorical_accuracy: 0.5988


671/Unknown  309s 460ms/step - loss: 1.0554 - sparse_categorical_accuracy: 0.5989


672/Unknown  310s 460ms/step - loss: 1.0550 - sparse_categorical_accuracy: 0.5990


673/Unknown  310s 460ms/step - loss: 1.0546 - sparse_categorical_accuracy: 0.5991


674/Unknown  310s 460ms/step - loss: 1.0542 - sparse_categorical_accuracy: 0.5992


675/Unknown  311s 460ms/step - loss: 1.0539 - sparse_categorical_accuracy: 0.5994


676/Unknown  311s 460ms/step - loss: 1.0535 - sparse_categorical_accuracy: 0.5995


677/Unknown  312s 460ms/step - loss: 1.0531 - sparse_categorical_accuracy: 0.5996


678/Unknown  312s 460ms/step - loss: 1.0527 - sparse_categorical_accuracy: 0.5997


679/Unknown  313s 460ms/step - loss: 1.0524 - sparse_categorical_accuracy: 0.5998


680/Unknown  313s 460ms/step - loss: 1.0520 - sparse_categorical_accuracy: 0.6000


681/Unknown  313s 459ms/step - loss: 1.0516 - sparse_categorical_accuracy: 0.6001


682/Unknown  314s 459ms/step - loss: 1.0512 - sparse_categorical_accuracy: 0.6002


683/Unknown  314s 459ms/step - loss: 1.0509 - sparse_categorical_accuracy: 0.6003


684/Unknown  315s 459ms/step - loss: 1.0505 - sparse_categorical_accuracy: 0.6004


685/Unknown  315s 459ms/step - loss: 1.0501 - sparse_categorical_accuracy: 0.6005


686/Unknown  315s 459ms/step - loss: 1.0498 - sparse_categorical_accuracy: 0.6006


687/Unknown  316s 459ms/step - loss: 1.0494 - sparse_categorical_accuracy: 0.6008


688/Unknown  316s 459ms/step - loss: 1.0490 - sparse_categorical_accuracy: 0.6009


689/Unknown  317s 459ms/step - loss: 1.0487 - sparse_categorical_accuracy: 0.6010


690/Unknown  317s 459ms/step - loss: 1.0483 - sparse_categorical_accuracy: 0.6011


691/Unknown  318s 459ms/step - loss: 1.0479 - sparse_categorical_accuracy: 0.6012


692/Unknown  318s 459ms/step - loss: 1.0476 - sparse_categorical_accuracy: 0.6013


693/Unknown  319s 459ms/step - loss: 1.0472 - sparse_categorical_accuracy: 0.6015


694/Unknown  319s 459ms/step - loss: 1.0468 - sparse_categorical_accuracy: 0.6016


695/Unknown  320s 459ms/step - loss: 1.0465 - sparse_categorical_accuracy: 0.6017


696/Unknown  320s 459ms/step - loss: 1.0461 - sparse_categorical_accuracy: 0.6018


697/Unknown  320s 459ms/step - loss: 1.0458 - sparse_categorical_accuracy: 0.6019


698/Unknown  321s 459ms/step - loss: 1.0454 - sparse_categorical_accuracy: 0.6020


699/Unknown  321s 459ms/step - loss: 1.0450 - sparse_categorical_accuracy: 0.6021


700/Unknown  322s 459ms/step - loss: 1.0447 - sparse_categorical_accuracy: 0.6022


701/Unknown  322s 459ms/step - loss: 1.0443 - sparse_categorical_accuracy: 0.6024


702/Unknown  323s 459ms/step - loss: 1.0440 - sparse_categorical_accuracy: 0.6025


703/Unknown  323s 459ms/step - loss: 1.0436 - sparse_categorical_accuracy: 0.6026


704/Unknown  324s 459ms/step - loss: 1.0433 - sparse_categorical_accuracy: 0.6027


705/Unknown  324s 459ms/step - loss: 1.0429 - sparse_categorical_accuracy: 0.6028


706/Unknown  325s 459ms/step - loss: 1.0426 - sparse_categorical_accuracy: 0.6029


707/Unknown  325s 459ms/step - loss: 1.0422 - sparse_categorical_accuracy: 0.6030


708/Unknown  326s 459ms/step - loss: 1.0419 - sparse_categorical_accuracy: 0.6031


709/Unknown  326s 459ms/step - loss: 1.0415 - sparse_categorical_accuracy: 0.6032


710/Unknown  327s 459ms/step - loss: 1.0411 - sparse_categorical_accuracy: 0.6034


711/Unknown  327s 459ms/step - loss: 1.0408 - sparse_categorical_accuracy: 0.6035


712/Unknown  328s 459ms/step - loss: 1.0405 - sparse_categorical_accuracy: 0.6036


713/Unknown  328s 459ms/step - loss: 1.0401 - sparse_categorical_accuracy: 0.6037


714/Unknown  329s 459ms/step - loss: 1.0398 - sparse_categorical_accuracy: 0.6038


715/Unknown  329s 460ms/step - loss: 1.0394 - sparse_categorical_accuracy: 0.6039


716/Unknown  330s 460ms/step - loss: 1.0391 - sparse_categorical_accuracy: 0.6040


717/Unknown  330s 460ms/step - loss: 1.0387 - sparse_categorical_accuracy: 0.6041


718/Unknown  330s 460ms/step - loss: 1.0384 - sparse_categorical_accuracy: 0.6042


719/Unknown  331s 460ms/step - loss: 1.0380 - sparse_categorical_accuracy: 0.6043


720/Unknown  331s 460ms/step - loss: 1.0377 - sparse_categorical_accuracy: 0.6044


721/Unknown  332s 460ms/step - loss: 1.0373 - sparse_categorical_accuracy: 0.6046


722/Unknown  332s 460ms/step - loss: 1.0370 - sparse_categorical_accuracy: 0.6047


723/Unknown  333s 459ms/step - loss: 1.0367 - sparse_categorical_accuracy: 0.6048


724/Unknown  333s 459ms/step - loss: 1.0363 - sparse_categorical_accuracy: 0.6049


725/Unknown  333s 459ms/step - loss: 1.0360 - sparse_categorical_accuracy: 0.6050


726/Unknown  334s 459ms/step - loss: 1.0356 - sparse_categorical_accuracy: 0.6051


727/Unknown  334s 459ms/step - loss: 1.0353 - sparse_categorical_accuracy: 0.6052


728/Unknown  335s 459ms/step - loss: 1.0350 - sparse_categorical_accuracy: 0.6053


729/Unknown  335s 459ms/step - loss: 1.0346 - sparse_categorical_accuracy: 0.6054


730/Unknown  336s 459ms/step - loss: 1.0343 - sparse_categorical_accuracy: 0.6055


731/Unknown  336s 459ms/step - loss: 1.0340 - sparse_categorical_accuracy: 0.6056


732/Unknown  336s 459ms/step - loss: 1.0336 - sparse_categorical_accuracy: 0.6057


733/Unknown  337s 459ms/step - loss: 1.0333 - sparse_categorical_accuracy: 0.6058


734/Unknown  337s 459ms/step - loss: 1.0330 - sparse_categorical_accuracy: 0.6059


735/Unknown  338s 459ms/step - loss: 1.0326 - sparse_categorical_accuracy: 0.6060


736/Unknown  338s 459ms/step - loss: 1.0323 - sparse_categorical_accuracy: 0.6061


737/Unknown  339s 459ms/step - loss: 1.0320 - sparse_categorical_accuracy: 0.6062


738/Unknown  339s 459ms/step - loss: 1.0316 - sparse_categorical_accuracy: 0.6064


739/Unknown  340s 459ms/step - loss: 1.0313 - sparse_categorical_accuracy: 0.6065


740/Unknown  340s 459ms/step - loss: 1.0310 - sparse_categorical_accuracy: 0.6066


741/Unknown  340s 459ms/step - loss: 1.0306 - sparse_categorical_accuracy: 0.6067


742/Unknown  341s 459ms/step - loss: 1.0303 - sparse_categorical_accuracy: 0.6068


743/Unknown  341s 459ms/step - loss: 1.0300 - sparse_categorical_accuracy: 0.6069


744/Unknown  342s 459ms/step - loss: 1.0296 - sparse_categorical_accuracy: 0.6070


745/Unknown  342s 459ms/step - loss: 1.0293 - sparse_categorical_accuracy: 0.6071


746/Unknown  343s 459ms/step - loss: 1.0290 - sparse_categorical_accuracy: 0.6072


747/Unknown  343s 459ms/step - loss: 1.0287 - sparse_categorical_accuracy: 0.6073


748/Unknown  344s 459ms/step - loss: 1.0283 - sparse_categorical_accuracy: 0.6074


749/Unknown  344s 459ms/step - loss: 1.0280 - sparse_categorical_accuracy: 0.6075


750/Unknown  345s 459ms/step - loss: 1.0277 - sparse_categorical_accuracy: 0.6076


751/Unknown  345s 459ms/step - loss: 1.0274 - sparse_categorical_accuracy: 0.6077


752/Unknown  346s 459ms/step - loss: 1.0271 - sparse_categorical_accuracy: 0.6078


753/Unknown  346s 459ms/step - loss: 1.0267 - sparse_categorical_accuracy: 0.6079


754/Unknown  347s 459ms/step - loss: 1.0264 - sparse_categorical_accuracy: 0.6080


755/Unknown  347s 459ms/step - loss: 1.0261 - sparse_categorical_accuracy: 0.6081


756/Unknown  348s 459ms/step - loss: 1.0258 - sparse_categorical_accuracy: 0.6082


757/Unknown  348s 459ms/step - loss: 1.0255 - sparse_categorical_accuracy: 0.6083


758/Unknown  349s 459ms/step - loss: 1.0251 - sparse_categorical_accuracy: 0.6084


759/Unknown  349s 459ms/step - loss: 1.0248 - sparse_categorical_accuracy: 0.6085


760/Unknown  350s 459ms/step - loss: 1.0245 - sparse_categorical_accuracy: 0.6086


761/Unknown  350s 459ms/step - loss: 1.0242 - sparse_categorical_accuracy: 0.6087


762/Unknown  351s 459ms/step - loss: 1.0239 - sparse_categorical_accuracy: 0.6088


763/Unknown  351s 459ms/step - loss: 1.0236 - sparse_categorical_accuracy: 0.6089


764/Unknown  352s 459ms/step - loss: 1.0232 - sparse_categorical_accuracy: 0.6090


765/Unknown  352s 460ms/step - loss: 1.0229 - sparse_categorical_accuracy: 0.6091


766/Unknown  353s 460ms/step - loss: 1.0226 - sparse_categorical_accuracy: 0.6092


767/Unknown  353s 460ms/step - loss: 1.0223 - sparse_categorical_accuracy: 0.6093


768/Unknown  354s 460ms/step - loss: 1.0220 - sparse_categorical_accuracy: 0.6094


769/Unknown  354s 460ms/step - loss: 1.0217 - sparse_categorical_accuracy: 0.6095


770/Unknown  354s 460ms/step - loss: 1.0214 - sparse_categorical_accuracy: 0.6096


771/Unknown  355s 459ms/step - loss: 1.0211 - sparse_categorical_accuracy: 0.6097


772/Unknown  355s 459ms/step - loss: 1.0207 - sparse_categorical_accuracy: 0.6098


773/Unknown  356s 459ms/step - loss: 1.0204 - sparse_categorical_accuracy: 0.6099


774/Unknown  356s 459ms/step - loss: 1.0201 - sparse_categorical_accuracy: 0.6100


775/Unknown  357s 459ms/step - loss: 1.0198 - sparse_categorical_accuracy: 0.6101


776/Unknown  357s 459ms/step - loss: 1.0195 - sparse_categorical_accuracy: 0.6102


777/Unknown  358s 460ms/step - loss: 1.0192 - sparse_categorical_accuracy: 0.6103


778/Unknown  358s 460ms/step - loss: 1.0189 - sparse_categorical_accuracy: 0.6103


779/Unknown  359s 460ms/step - loss: 1.0186 - sparse_categorical_accuracy: 0.6104


780/Unknown  359s 460ms/step - loss: 1.0183 - sparse_categorical_accuracy: 0.6105


781/Unknown  360s 460ms/step - loss: 1.0180 - sparse_categorical_accuracy: 0.6106


782/Unknown  360s 460ms/step - loss: 1.0177 - sparse_categorical_accuracy: 0.6107


783/Unknown  360s 460ms/step - loss: 1.0174 - sparse_categorical_accuracy: 0.6108


784/Unknown  361s 460ms/step - loss: 1.0171 - sparse_categorical_accuracy: 0.6109


785/Unknown  361s 460ms/step - loss: 1.0168 - sparse_categorical_accuracy: 0.6110


786/Unknown  362s 460ms/step - loss: 1.0165 - sparse_categorical_accuracy: 0.6111


787/Unknown  362s 460ms/step - loss: 1.0162 - sparse_categorical_accuracy: 0.6112


788/Unknown  363s 460ms/step - loss: 1.0159 - sparse_categorical_accuracy: 0.6113


789/Unknown  363s 460ms/step - loss: 1.0156 - sparse_categorical_accuracy: 0.6114


790/Unknown  364s 460ms/step - loss: 1.0153 - sparse_categorical_accuracy: 0.6115


791/Unknown  364s 460ms/step - loss: 1.0150 - sparse_categorical_accuracy: 0.6116


792/Unknown  365s 460ms/step - loss: 1.0147 - sparse_categorical_accuracy: 0.6117


793/Unknown  365s 460ms/step - loss: 1.0144 - sparse_categorical_accuracy: 0.6118


794/Unknown  366s 460ms/step - loss: 1.0141 - sparse_categorical_accuracy: 0.6119


795/Unknown  366s 460ms/step - loss: 1.0138 - sparse_categorical_accuracy: 0.6120


796/Unknown  367s 460ms/step - loss: 1.0135 - sparse_categorical_accuracy: 0.6120


797/Unknown  367s 460ms/step - loss: 1.0132 - sparse_categorical_accuracy: 0.6121


798/Unknown  367s 460ms/step - loss: 1.0129 - sparse_categorical_accuracy: 0.6122


799/Unknown  368s 460ms/step - loss: 1.0126 - sparse_categorical_accuracy: 0.6123


800/Unknown  368s 460ms/step - loss: 1.0123 - sparse_categorical_accuracy: 0.6124


801/Unknown  369s 460ms/step - loss: 1.0120 - sparse_categorical_accuracy: 0.6125


802/Unknown  369s 460ms/step - loss: 1.0117 - sparse_categorical_accuracy: 0.6126


803/Unknown  370s 460ms/step - loss: 1.0114 - sparse_categorical_accuracy: 0.6127


804/Unknown  370s 460ms/step - loss: 1.0111 - sparse_categorical_accuracy: 0.6128


805/Unknown  371s 460ms/step - loss: 1.0108 - sparse_categorical_accuracy: 0.6129


806/Unknown  371s 460ms/step - loss: 1.0106 - sparse_categorical_accuracy: 0.6130


807/Unknown  372s 460ms/step - loss: 1.0103 - sparse_categorical_accuracy: 0.6131


808/Unknown  372s 460ms/step - loss: 1.0100 - sparse_categorical_accuracy: 0.6131


809/Unknown  372s 459ms/step - loss: 1.0097 - sparse_categorical_accuracy: 0.6132


810/Unknown  373s 459ms/step - loss: 1.0094 - sparse_categorical_accuracy: 0.6133


811/Unknown  373s 459ms/step - loss: 1.0091 - sparse_categorical_accuracy: 0.6134


812/Unknown  373s 459ms/step - loss: 1.0088 - sparse_categorical_accuracy: 0.6135


813/Unknown  374s 459ms/step - loss: 1.0085 - sparse_categorical_accuracy: 0.6136


814/Unknown  374s 459ms/step - loss: 1.0082 - sparse_categorical_accuracy: 0.6137


815/Unknown  375s 459ms/step - loss: 1.0080 - sparse_categorical_accuracy: 0.6138


816/Unknown  375s 459ms/step - loss: 1.0077 - sparse_categorical_accuracy: 0.6139


817/Unknown  375s 459ms/step - loss: 1.0074 - sparse_categorical_accuracy: 0.6140


818/Unknown  376s 459ms/step - loss: 1.0071 - sparse_categorical_accuracy: 0.6140


819/Unknown  376s 459ms/step - loss: 1.0068 - sparse_categorical_accuracy: 0.6141


820/Unknown  377s 459ms/step - loss: 1.0065 - sparse_categorical_accuracy: 0.6142


821/Unknown  377s 459ms/step - loss: 1.0063 - sparse_categorical_accuracy: 0.6143


822/Unknown  378s 459ms/step - loss: 1.0060 - sparse_categorical_accuracy: 0.6144


823/Unknown  378s 459ms/step - loss: 1.0057 - sparse_categorical_accuracy: 0.6145


824/Unknown  379s 459ms/step - loss: 1.0054 - sparse_categorical_accuracy: 0.6146


825/Unknown  379s 459ms/step - loss: 1.0051 - sparse_categorical_accuracy: 0.6147


826/Unknown  380s 459ms/step - loss: 1.0048 - sparse_categorical_accuracy: 0.6148


827/Unknown  380s 459ms/step - loss: 1.0046 - sparse_categorical_accuracy: 0.6148


828/Unknown  381s 459ms/step - loss: 1.0043 - sparse_categorical_accuracy: 0.6149


829/Unknown  381s 459ms/step - loss: 1.0040 - sparse_categorical_accuracy: 0.6150


830/Unknown  382s 459ms/step - loss: 1.0037 - sparse_categorical_accuracy: 0.6151


831/Unknown  382s 459ms/step - loss: 1.0034 - sparse_categorical_accuracy: 0.6152


832/Unknown  383s 459ms/step - loss: 1.0032 - sparse_categorical_accuracy: 0.6153


833/Unknown  383s 459ms/step - loss: 1.0029 - sparse_categorical_accuracy: 0.6154


834/Unknown  384s 459ms/step - loss: 1.0026 - sparse_categorical_accuracy: 0.6155


835/Unknown  384s 459ms/step - loss: 1.0023 - sparse_categorical_accuracy: 0.6155


836/Unknown  385s 459ms/step - loss: 1.0021 - sparse_categorical_accuracy: 0.6156


837/Unknown  385s 459ms/step - loss: 1.0018 - sparse_categorical_accuracy: 0.6157


838/Unknown  385s 459ms/step - loss: 1.0015 - sparse_categorical_accuracy: 0.6158


839/Unknown  386s 459ms/step - loss: 1.0012 - sparse_categorical_accuracy: 0.6159


840/Unknown  386s 459ms/step - loss: 1.0010 - sparse_categorical_accuracy: 0.6160


841/Unknown  387s 459ms/step - loss: 1.0007 - sparse_categorical_accuracy: 0.6161


842/Unknown  387s 459ms/step - loss: 1.0004 - sparse_categorical_accuracy: 0.6162


843/Unknown  388s 459ms/step - loss: 1.0001 - sparse_categorical_accuracy: 0.6162


844/Unknown  388s 459ms/step - loss: 0.9999 - sparse_categorical_accuracy: 0.6163


845/Unknown  389s 459ms/step - loss: 0.9996 - sparse_categorical_accuracy: 0.6164


846/Unknown  389s 459ms/step - loss: 0.9993 - sparse_categorical_accuracy: 0.6165


847/Unknown  390s 459ms/step - loss: 0.9990 - sparse_categorical_accuracy: 0.6166


848/Unknown  390s 460ms/step - loss: 0.9988 - sparse_categorical_accuracy: 0.6167


849/Unknown  391s 460ms/step - loss: 0.9985 - sparse_categorical_accuracy: 0.6167


850/Unknown  391s 460ms/step - loss: 0.9982 - sparse_categorical_accuracy: 0.6168


851/Unknown  392s 460ms/step - loss: 0.9980 - sparse_categorical_accuracy: 0.6169


852/Unknown  392s 460ms/step - loss: 0.9977 - sparse_categorical_accuracy: 0.6170


853/Unknown  393s 460ms/step - loss: 0.9974 - sparse_categorical_accuracy: 0.6171


854/Unknown  393s 460ms/step - loss: 0.9972 - sparse_categorical_accuracy: 0.6172


855/Unknown  394s 460ms/step - loss: 0.9969 - sparse_categorical_accuracy: 0.6173


856/Unknown  394s 460ms/step - loss: 0.9966 - sparse_categorical_accuracy: 0.6173


857/Unknown  394s 460ms/step - loss: 0.9964 - sparse_categorical_accuracy: 0.6174


858/Unknown  395s 460ms/step - loss: 0.9961 - sparse_categorical_accuracy: 0.6175


859/Unknown  395s 460ms/step - loss: 0.9958 - sparse_categorical_accuracy: 0.6176


860/Unknown  396s 460ms/step - loss: 0.9956 - sparse_categorical_accuracy: 0.6177


861/Unknown  396s 460ms/step - loss: 0.9953 - sparse_categorical_accuracy: 0.6178


862/Unknown  397s 460ms/step - loss: 0.9950 - sparse_categorical_accuracy: 0.6178


863/Unknown  397s 459ms/step - loss: 0.9948 - sparse_categorical_accuracy: 0.6179


864/Unknown  397s 459ms/step - loss: 0.9945 - sparse_categorical_accuracy: 0.6180


865/Unknown  398s 459ms/step - loss: 0.9942 - sparse_categorical_accuracy: 0.6181


866/Unknown  398s 459ms/step - loss: 0.9940 - sparse_categorical_accuracy: 0.6182


867/Unknown  399s 459ms/step - loss: 0.9937 - sparse_categorical_accuracy: 0.6182


868/Unknown  399s 459ms/step - loss: 0.9935 - sparse_categorical_accuracy: 0.6183


869/Unknown  399s 459ms/step - loss: 0.9932 - sparse_categorical_accuracy: 0.6184


870/Unknown  400s 459ms/step - loss: 0.9929 - sparse_categorical_accuracy: 0.6185


871/Unknown  400s 459ms/step - loss: 0.9927 - sparse_categorical_accuracy: 0.6186


872/Unknown  401s 459ms/step - loss: 0.9924 - sparse_categorical_accuracy: 0.6187


873/Unknown  401s 459ms/step - loss: 0.9922 - sparse_categorical_accuracy: 0.6187


874/Unknown  402s 459ms/step - loss: 0.9919 - sparse_categorical_accuracy: 0.6188


875/Unknown  402s 459ms/step - loss: 0.9916 - sparse_categorical_accuracy: 0.6189


876/Unknown  403s 459ms/step - loss: 0.9914 - sparse_categorical_accuracy: 0.6190


877/Unknown  403s 459ms/step - loss: 0.9911 - sparse_categorical_accuracy: 0.6191


878/Unknown  404s 459ms/step - loss: 0.9909 - sparse_categorical_accuracy: 0.6191


879/Unknown  404s 459ms/step - loss: 0.9906 - sparse_categorical_accuracy: 0.6192


880/Unknown  404s 459ms/step - loss: 0.9904 - sparse_categorical_accuracy: 0.6193


881/Unknown  405s 459ms/step - loss: 0.9901 - sparse_categorical_accuracy: 0.6194


882/Unknown  405s 459ms/step - loss: 0.9898 - sparse_categorical_accuracy: 0.6195


883/Unknown  406s 459ms/step - loss: 0.9896 - sparse_categorical_accuracy: 0.6195


884/Unknown  406s 459ms/step - loss: 0.9893 - sparse_categorical_accuracy: 0.6196


885/Unknown  406s 459ms/step - loss: 0.9891 - sparse_categorical_accuracy: 0.6197


886/Unknown  407s 459ms/step - loss: 0.9888 - sparse_categorical_accuracy: 0.6198


887/Unknown  407s 458ms/step - loss: 0.9886 - sparse_categorical_accuracy: 0.6199


888/Unknown  408s 458ms/step - loss: 0.9883 - sparse_categorical_accuracy: 0.6199


889/Unknown  408s 458ms/step - loss: 0.9881 - sparse_categorical_accuracy: 0.6200


890/Unknown  408s 458ms/step - loss: 0.9878 - sparse_categorical_accuracy: 0.6201


891/Unknown  409s 458ms/step - loss: 0.9876 - sparse_categorical_accuracy: 0.6202


892/Unknown  409s 458ms/step - loss: 0.9873 - sparse_categorical_accuracy: 0.6203


893/Unknown  410s 458ms/step - loss: 0.9871 - sparse_categorical_accuracy: 0.6203


894/Unknown  410s 458ms/step - loss: 0.9868 - sparse_categorical_accuracy: 0.6204


895/Unknown  411s 458ms/step - loss: 0.9866 - sparse_categorical_accuracy: 0.6205


896/Unknown  411s 458ms/step - loss: 0.9863 - sparse_categorical_accuracy: 0.6206


897/Unknown  412s 458ms/step - loss: 0.9861 - sparse_categorical_accuracy: 0.6206


898/Unknown  412s 458ms/step - loss: 0.9858 - sparse_categorical_accuracy: 0.6207


899/Unknown  413s 458ms/step - loss: 0.9856 - sparse_categorical_accuracy: 0.6208


900/Unknown  413s 459ms/step - loss: 0.9853 - sparse_categorical_accuracy: 0.6209


901/Unknown  414s 459ms/step - loss: 0.9851 - sparse_categorical_accuracy: 0.6210


902/Unknown  414s 458ms/step - loss: 0.9848 - sparse_categorical_accuracy: 0.6210


903/Unknown  414s 458ms/step - loss: 0.9846 - sparse_categorical_accuracy: 0.6211


904/Unknown  415s 458ms/step - loss: 0.9843 - sparse_categorical_accuracy: 0.6212


905/Unknown  415s 458ms/step - loss: 0.9841 - sparse_categorical_accuracy: 0.6213


906/Unknown  416s 458ms/step - loss: 0.9838 - sparse_categorical_accuracy: 0.6213


907/Unknown  416s 458ms/step - loss: 0.9836 - sparse_categorical_accuracy: 0.6214


908/Unknown  416s 458ms/step - loss: 0.9834 - sparse_categorical_accuracy: 0.6215


909/Unknown  417s 458ms/step - loss: 0.9831 - sparse_categorical_accuracy: 0.6216


910/Unknown  417s 458ms/step - loss: 0.9829 - sparse_categorical_accuracy: 0.6216


911/Unknown  418s 458ms/step - loss: 0.9826 - sparse_categorical_accuracy: 0.6217


912/Unknown  418s 458ms/step - loss: 0.9824 - sparse_categorical_accuracy: 0.6218


913/Unknown  418s 458ms/step - loss: 0.9821 - sparse_categorical_accuracy: 0.6219


914/Unknown  419s 458ms/step - loss: 0.9819 - sparse_categorical_accuracy: 0.6219


915/Unknown  419s 457ms/step - loss: 0.9817 - sparse_categorical_accuracy: 0.6220


916/Unknown  420s 457ms/step - loss: 0.9814 - sparse_categorical_accuracy: 0.6221


917/Unknown  420s 458ms/step - loss: 0.9812 - sparse_categorical_accuracy: 0.6222


918/Unknown  421s 458ms/step - loss: 0.9809 - sparse_categorical_accuracy: 0.6222


919/Unknown  421s 458ms/step - loss: 0.9807 - sparse_categorical_accuracy: 0.6223


920/Unknown  421s 457ms/step - loss: 0.9805 - sparse_categorical_accuracy: 0.6224


921/Unknown  422s 458ms/step - loss: 0.9802 - sparse_categorical_accuracy: 0.6225


922/Unknown  422s 458ms/step - loss: 0.9800 - sparse_categorical_accuracy: 0.6225


923/Unknown  423s 458ms/step - loss: 0.9797 - sparse_categorical_accuracy: 0.6226


924/Unknown  423s 458ms/step - loss: 0.9795 - sparse_categorical_accuracy: 0.6227


925/Unknown  424s 458ms/step - loss: 0.9793 - sparse_categorical_accuracy: 0.6228


926/Unknown  424s 458ms/step - loss: 0.9790 - sparse_categorical_accuracy: 0.6228


927/Unknown  425s 458ms/step - loss: 0.9788 - sparse_categorical_accuracy: 0.6229


928/Unknown  425s 458ms/step - loss: 0.9785 - sparse_categorical_accuracy: 0.6230


929/Unknown  426s 458ms/step - loss: 0.9783 - sparse_categorical_accuracy: 0.6231


930/Unknown  426s 458ms/step - loss: 0.9781 - sparse_categorical_accuracy: 0.6231


931/Unknown  427s 458ms/step - loss: 0.9778 - sparse_categorical_accuracy: 0.6232


932/Unknown  427s 458ms/step - loss: 0.9776 - sparse_categorical_accuracy: 0.6233


933/Unknown  428s 458ms/step - loss: 0.9774 - sparse_categorical_accuracy: 0.6234


934/Unknown  428s 458ms/step - loss: 0.9771 - sparse_categorical_accuracy: 0.6234


935/Unknown  429s 458ms/step - loss: 0.9769 - sparse_categorical_accuracy: 0.6235


936/Unknown  429s 458ms/step - loss: 0.9767 - sparse_categorical_accuracy: 0.6236


937/Unknown  429s 458ms/step - loss: 0.9764 - sparse_categorical_accuracy: 0.6236


938/Unknown  430s 458ms/step - loss: 0.9762 - sparse_categorical_accuracy: 0.6237


939/Unknown  430s 458ms/step - loss: 0.9760 - sparse_categorical_accuracy: 0.6238


940/Unknown  431s 458ms/step - loss: 0.9757 - sparse_categorical_accuracy: 0.6239


941/Unknown  431s 458ms/step - loss: 0.9755 - sparse_categorical_accuracy: 0.6239


942/Unknown  432s 458ms/step - loss: 0.9753 - sparse_categorical_accuracy: 0.6240


943/Unknown  432s 458ms/step - loss: 0.9750 - sparse_categorical_accuracy: 0.6241


944/Unknown  433s 458ms/step - loss: 0.9748 - sparse_categorical_accuracy: 0.6242


945/Unknown  433s 458ms/step - loss: 0.9746 - sparse_categorical_accuracy: 0.6242


946/Unknown  434s 458ms/step - loss: 0.9744 - sparse_categorical_accuracy: 0.6243


947/Unknown  434s 458ms/step - loss: 0.9741 - sparse_categorical_accuracy: 0.6244


948/Unknown  435s 458ms/step - loss: 0.9739 - sparse_categorical_accuracy: 0.6244


949/Unknown  435s 458ms/step - loss: 0.9737 - sparse_categorical_accuracy: 0.6245


950/Unknown  436s 458ms/step - loss: 0.9734 - sparse_categorical_accuracy: 0.6246


951/Unknown  436s 458ms/step - loss: 0.9732 - sparse_categorical_accuracy: 0.6247


952/Unknown  437s 458ms/step - loss: 0.9730 - sparse_categorical_accuracy: 0.6247


953/Unknown  437s 458ms/step - loss: 0.9727 - sparse_categorical_accuracy: 0.6248


954/Unknown  438s 458ms/step - loss: 0.9725 - sparse_categorical_accuracy: 0.6249


955/Unknown  438s 458ms/step - loss: 0.9723 - sparse_categorical_accuracy: 0.6249


956/Unknown  439s 458ms/step - loss: 0.9721 - sparse_categorical_accuracy: 0.6250


957/Unknown  439s 458ms/step - loss: 0.9718 - sparse_categorical_accuracy: 0.6251


958/Unknown  439s 458ms/step - loss: 0.9716 - sparse_categorical_accuracy: 0.6252


959/Unknown  440s 458ms/step - loss: 0.9714 - sparse_categorical_accuracy: 0.6252


960/Unknown  440s 458ms/step - loss: 0.9712 - sparse_categorical_accuracy: 0.6253


961/Unknown  441s 458ms/step - loss: 0.9709 - sparse_categorical_accuracy: 0.6254


962/Unknown  441s 458ms/step - loss: 0.9707 - sparse_categorical_accuracy: 0.6254


963/Unknown  442s 458ms/step - loss: 0.9705 - sparse_categorical_accuracy: 0.6255


964/Unknown  442s 458ms/step - loss: 0.9703 - sparse_categorical_accuracy: 0.6256


965/Unknown  443s 458ms/step - loss: 0.9700 - sparse_categorical_accuracy: 0.6256


966/Unknown  443s 458ms/step - loss: 0.9698 - sparse_categorical_accuracy: 0.6257


967/Unknown  444s 458ms/step - loss: 0.9696 - sparse_categorical_accuracy: 0.6258


968/Unknown  444s 458ms/step - loss: 0.9694 - sparse_categorical_accuracy: 0.6259


969/Unknown  445s 458ms/step - loss: 0.9692 - sparse_categorical_accuracy: 0.6259


970/Unknown  445s 458ms/step - loss: 0.9689 - sparse_categorical_accuracy: 0.6260


971/Unknown  446s 458ms/step - loss: 0.9687 - sparse_categorical_accuracy: 0.6261


972/Unknown  446s 459ms/step - loss: 0.9685 - sparse_categorical_accuracy: 0.6261


973/Unknown  447s 458ms/step - loss: 0.9683 - sparse_categorical_accuracy: 0.6262


974/Unknown  447s 458ms/step - loss: 0.9680 - sparse_categorical_accuracy: 0.6263


975/Unknown  447s 458ms/step - loss: 0.9678 - sparse_categorical_accuracy: 0.6263


976/Unknown  448s 458ms/step - loss: 0.9676 - sparse_categorical_accuracy: 0.6264


977/Unknown  448s 458ms/step - loss: 0.9674 - sparse_categorical_accuracy: 0.6265


978/Unknown  449s 458ms/step - loss: 0.9672 - sparse_categorical_accuracy: 0.6265


979/Unknown  449s 458ms/step - loss: 0.9669 - sparse_categorical_accuracy: 0.6266


980/Unknown  449s 458ms/step - loss: 0.9667 - sparse_categorical_accuracy: 0.6267


981/Unknown  450s 458ms/step - loss: 0.9665 - sparse_categorical_accuracy: 0.6268


982/Unknown  450s 458ms/step - loss: 0.9663 - sparse_categorical_accuracy: 0.6268


983/Unknown  451s 458ms/step - loss: 0.9661 - sparse_categorical_accuracy: 0.6269


984/Unknown  451s 458ms/step - loss: 0.9659 - sparse_categorical_accuracy: 0.6270


985/Unknown  451s 458ms/step - loss: 0.9656 - sparse_categorical_accuracy: 0.6270


986/Unknown  452s 458ms/step - loss: 0.9654 - sparse_categorical_accuracy: 0.6271


987/Unknown  452s 458ms/step - loss: 0.9652 - sparse_categorical_accuracy: 0.6272


988/Unknown  453s 458ms/step - loss: 0.9650 - sparse_categorical_accuracy: 0.6272


989/Unknown  453s 458ms/step - loss: 0.9648 - sparse_categorical_accuracy: 0.6273


990/Unknown  454s 458ms/step - loss: 0.9646 - sparse_categorical_accuracy: 0.6274


991/Unknown  454s 458ms/step - loss: 0.9643 - sparse_categorical_accuracy: 0.6274


992/Unknown  455s 458ms/step - loss: 0.9641 - sparse_categorical_accuracy: 0.6275


993/Unknown  455s 458ms/step - loss: 0.9639 - sparse_categorical_accuracy: 0.6276


994/Unknown  456s 458ms/step - loss: 0.9637 - sparse_categorical_accuracy: 0.6276


995/Unknown  456s 458ms/step - loss: 0.9635 - sparse_categorical_accuracy: 0.6277


996/Unknown  457s 458ms/step - loss: 0.9633 - sparse_categorical_accuracy: 0.6278


997/Unknown  457s 458ms/step - loss: 0.9631 - sparse_categorical_accuracy: 0.6278


998/Unknown  458s 458ms/step - loss: 0.9628 - sparse_categorical_accuracy: 0.6279


999/Unknown  458s 458ms/step - loss: 0.9626 - sparse_categorical_accuracy: 0.6280

1000/未知 459s 458ms/step - 损失: 0.9624 - 稀疏类别准确率: 0.6280

1001/未知 459s 458ms/step - 损失: 0.9622 - 稀疏类别准确率: 0.6281

1002/未知 460s 458ms/step - 损失: 0.9620 - 稀疏类别准确率: 0.6282

1003/未知 460s 458ms/step - 损失: 0.9618 - 稀疏类别准确率: 0.6282

1004/未知 461s 458ms/step - 损失: 0.9616 - 稀疏类别准确率: 0.6283

1005/未知 461s 458ms/step - 损失: 0.9614 - 稀疏类别准确率: 0.6284

1006/未知 462s 458ms/step - 损失: 0.9612 - 稀疏类别准确率: 0.6284

1007/未知 462s 458ms/step - 损失: 0.9609 - 稀疏类别准确率: 0.6285

1008/未知 462s 458ms/step - 损失: 0.9607 - 稀疏类别准确率: 0.6286

1009/未知 463s 458ms/step - 损失: 0.9605 - 稀疏类别准确率: 0.6286

1010/未知 463s 458ms/step - 损失: 0.9603 - 稀疏类别准确率: 0.6287

1011/未知 464s 458ms/step - 损失: 0.9601 - 稀疏类别准确率: 0.6287

1012/未知 465s 458ms/step - 损失: 0.9599 - 稀疏类别准确率: 0.6288

1013/未知 465s 458ms/step - 损失: 0.9597 - 稀疏类别准确率: 0.6289

1014/未知 465s 459ms/step - 损失: 0.9595 - 稀疏类别准确率: 0.6289

1015/未知 466s 459ms/step - 损失: 0.9593 - 稀疏类别准确率: 0.6290

1016/未知 466s 459ms/step - 损失: 0.9591 - 稀疏类别准确率: 0.6291

1017/未知 467s 459ms/step - 损失: 0.9589 - 稀疏类别准确率: 0.6291

1018/未知 467s 459ms/step - 损失: 0.9587 - 稀疏类别准确率: 0.6292

1019/未知 468s 459ms/step - 损失: 0.9584 - 稀疏类别准确率: 0.6293

1020/未知 468s 459ms/step - 损失: 0.9582 - 稀疏类别准确率: 0.6293

1021/未知 469s 459ms/step - 损失: 0.9580 - 稀疏类别准确率: 0.6294

1022/未知 469s 459ms/step - 损失: 0.9578 - 稀疏类别准确率: 0.6295

1023/未知 470s 459ms/step - 损失: 0.9576 - 稀疏类别准确率: 0.6295

1024/未知 470s 459ms/step - 损失: 0.9574 - 稀疏类别准确率: 0.6296

1025/未知 471s 459ms/step - 损失: 0.9572 - 稀疏类别准确率: 0.6297

1026/未知 471s 459ms/step - 损失: 0.9570 - 稀疏类别准确率: 0.6297

1027/未知 472s 459ms/step - 损失: 0.9568 - 稀疏类别准确率: 0.6298

1028/未知 472s 459ms/step - 损失: 0.9566 - 稀疏类别准确率: 0.6298

1029/未知 473s 459ms/step - 损失: 0.9564 - 稀疏类别准确率: 0.6299

1030/未知 473s 459ms/step - 损失: 0.9562 - 稀疏类别准确率: 0.6300

1031/未知 474s 459ms/step - 损失: 0.9560 - 稀疏类别准确率: 0.6300

1032/未知 474s 459ms/step - 损失: 0.9558 - 稀疏类别准确率: 0.6301

1033/未知 475s 459ms/step - 损失: 0.9556 - 稀疏类别准确率: 0.6302

1034/未知 475s 459ms/step - 损失: 0.9554 - 稀疏类别准确率: 0.6302

1035/未知 476s 459ms/step - 损失: 0.9552 - 稀疏类别准确率: 0.6303

1036/未知 476s 459ms/step - 损失: 0.9550 - 稀疏类别准确率: 0.6304

1037/未知 477s 459ms/step - 损失: 0.9548 - 稀疏类别准确率: 0.6304

1038/未知 477s 459ms/step - 损失: 0.9546 - 稀疏类别准确率: 0.6305

1039/未知 478s 459ms/step - 损失: 0.9544 - 稀疏类别准确率: 0.6305

1040/未知 478s 459ms/step - 损失: 0.9542 - 稀疏类别准确率: 0.6306

1041/未知 479s 459ms/step - 损失: 0.9540 - 稀疏类别准确率: 0.6307

1042/未知 479s 459ms/step - 损失: 0.9538 - 稀疏类别准确率: 0.6307

1043/未知 480s 459ms/step - 损失: 0.9536 - 稀疏类别准确率: 0.6308

1044/未知 480s 459ms/step - 损失: 0.9534 - 稀疏类别准确率: 0.6309

1045/未知 481s 459ms/step - 损失: 0.9532 - 稀疏类别准确率: 0.6309

1046/未知 481s 459ms/step - 损失: 0.9530 - 稀疏类别准确率: 0.6310

1047/未知 482s 459ms/step - 损失: 0.9528 - 稀疏类别准确率: 0.6310

1048/未知 482s 459ms/step - 损失: 0.9526 - 稀疏类别准确率: 0.6311

1049/未知 483s 459ms/step - 损失: 0.9524 - 稀疏类别准确率: 0.6312

1050/未知 483s 460ms/step - 损失: 0.9522 - 稀疏类别准确率: 0.6312

1051/未知 484s 460ms/step - 损失: 0.9520 - 稀疏类别准确率: 0.6313

1052/未知 484s 460ms/step - 损失: 0.9518 - 稀疏类别准确率: 0.6314

1053/未知 484s 460ms/step - 损失: 0.9516 - 稀疏类别准确率: 0.6314

1054/未知 485s 460ms/step - 损失: 0.9514 - 稀疏类别准确率: 0.6315

1055/未知 485s 460ms/step - 损失: 0.9512 - 稀疏类别准确率: 0.6315

1056/未知 486s 460ms/step - 损失: 0.9510 - 稀疏类别准确率: 0.6316

1057/未知 486s 460ms/step - 损失: 0.9508 - 稀疏类别准确率: 0.6317

1058/未知 487s 460ms/step - 损失: 0.9506 - 稀疏类别准确率: 0.6317

1059/未知 487s 460ms/step - 损失: 0.9504 - 稀疏类别准确率: 0.6318

1060/未知 488s 460ms/step - 损失: 0.9502 - 稀疏类别准确率: 0.6318

1061/未知 488s 460ms/step - 损失: 0.9500 - 稀疏类别准确率: 0.6319

1062/未知 489s 460ms/step - 损失: 0.9498 - 稀疏类别准确率: 0.6320

1063/未知 489s 460ms/step - 损失: 0.9496 - 稀疏类别准确率: 0.6320

1064/未知 490s 460ms/step - 损失: 0.9495 - 稀疏类别准确率: 0.6321

1065/未知 490s 460ms/step - 损失: 0.9493 - 稀疏类别准确率: 0.6321

1066/未知 491s 460ms/step - 损失: 0.9491 - 稀疏类别准确率: 0.6322

1067/未知 491s 460ms/step - 损失: 0.9489 - 稀疏类别准确率: 0.6323

1068/未知 492s 460ms/step - 损失: 0.9487 - 稀疏类别准确率: 0.6323

1069/未知 492s 460ms/step - 损失: 0.9485 - 稀疏类别准确率: 0.6324

1070/未知 493s 460ms/step - 损失: 0.9483 - 稀疏类别准确率: 0.6324

1071/未知 493s 460ms/step - 损失: 0.9481 - 稀疏类别准确率: 0.6325

1072/未知 494s 460ms/step - 损失: 0.9479 - 稀疏类别准确率: 0.6326

1073/未知 494s 460ms/step - 损失: 0.9477 - 稀疏类别准确率: 0.6326

1074/未知 495s 460ms/step - 损失: 0.9475 - 稀疏类别准确率: 0.6327

1075/未知 495s 460ms/step - 损失: 0.9473 - 稀疏类别准确率: 0.6327

1076/未知 496s 460ms/step - 损失: 0.9471 - 稀疏类别准确率: 0.6328

1077/未知 496s 460ms/step - 损失: 0.9470 - 稀疏类别准确率: 0.6329

1078/未知 496s 460ms/step - 损失: 0.9468 - 稀疏类别准确率: 0.6329

1079/未知 497s 460ms/step - 损失: 0.9466 - 稀疏类别准确率: 0.6330

1080/未知 497s 460ms/step - 损失: 0.9464 - 稀疏类别准确率: 0.6330

1081/未知 498s 460ms/step - 损失: 0.9462 - 稀疏类别准确率: 0.6331

1082/未知 498s 460ms/step - 损失: 0.9460 - 稀疏类别准确率: 0.6332

1083/未知 499s 460ms/step - 损失: 0.9458 - 稀疏类别准确率: 0.6332

1084/未知 499s 460ms/step - 损失: 0.9456 - 稀疏类别准确率: 0.6333

1085/未知 500s 460ms/step - 损失: 0.9454 - 稀疏类别准确率: 0.6333

1086/未知 500s 460ms/step - 损失: 0.9453 - 稀疏类别准确率: 0.6334

1087/未知 501s 460ms/step - 损失: 0.9451 - 稀疏类别准确率: 0.6335

1088/未知 501s 460ms/step - 损失: 0.9449 - 稀疏类别准确率: 0.6335

1089/未知 502s 460ms/step - 损失: 0.9447 - 稀疏类别准确率: 0.6336

1090/未知 502s 460ms/step - 损失: 0.9445 - 稀疏类别准确率: 0.6336

1091/未知 503s 460ms/step - 损失: 0.9443 - 稀疏类别准确率: 0.6337

1092/未知 503s 460ms/step - 损失: 0.9441 - 稀疏类别准确率: 0.6337

1093/未知 503s 460ms/step - 损失: 0.9439 - 稀疏类别准确率: 0.6338

1094/未知 504s 460ms/step - 损失: 0.9438 - 稀疏类别准确率: 0.6339

1095/未知 504s 460ms/step - 损失: 0.9436 - 稀疏类别准确率: 0.6339

1096/未知 505s 460ms/step - 损失: 0.9434 - 稀疏类别准确率: 0.6340

1097/未知 505s 460ms/step - 损失: 0.9432 - 稀疏类别准确率: 0.6340

1098/未知 506s 460ms/step - 损失: 0.9430 - 稀疏类别准确率: 0.6341

1099/未知 506s 460ms/step - 损失: 0.9428 - 稀疏类别准确率: 0.6342

1100/未知 507s 460ms/step - 损失: 0.9427 - 稀疏类别准确率: 0.6342

1101/未知 507s 460ms/step - 损失: 0.9425 - 稀疏类别准确率: 0.6343

1102/未知 508s 460ms/step - 损失: 0.9423 - 稀疏类别准确率: 0.6343

1103/未知 508s 460ms/step - 损失: 0.9421 - 稀疏类别准确率: 0.6344

1104/未知 508s 460ms/step - 损失: 0.9419 - 稀疏类别准确率: 0.6344

1105/未知 509s 460ms/step - 损失: 0.9417 - 稀疏类别准确率: 0.6345

1106/未知 509s 460ms/step - 损失: 0.9416 - 稀疏类别准确率: 0.6346

1107/未知 510s 460ms/step - 损失: 0.9414 - 稀疏类别准确率: 0.6346

1108/未知 510s 460ms/step - 损失: 0.9412 - 稀疏类别准确率: 0.6347

1109/未知 510s 460ms/step - 损失: 0.9410 - 稀疏类别准确率: 0.6347

1110/未知 511s 459ms/step - 损失: 0.9408 - 稀疏类别准确率: 0.6348

1111/未知 511s 459ms/step - 损失: 0.9406 - 稀疏类别准确率: 0.6348

1112/未知 511s 459ms/step - 损失: 0.9405 - 稀疏类别准确率: 0.6349

1113/未知 512s 459ms/step - 损失: 0.9403 - 稀疏类别准确率: 0.6349

1114/未知 512s 459ms/step - 损失: 0.9401 - 稀疏类别准确率: 0.6350

1115/未知 512s 459ms/step - 损失: 0.9399 - 稀疏类别准确率: 0.6351

1116/未知 513s 459ms/step - 损失: 0.9397 - 稀疏类别准确率: 0.6351

1117/未知 513s 459ms/step - 损失: 0.9396 - 稀疏类别准确率: 0.6352

1118/未知 513s 459ms/step - 损失: 0.9394 - 稀疏类别准确率: 0.6352

1119/未知 514s 459ms/step - 损失: 0.9392 - 稀疏类别准确率: 0.6353

1120/未知 514s 458ms/step - 损失: 0.9390 - 稀疏类别准确率: 0.6353

1121/未知 515s 458ms/step - 损失: 0.9388 - 稀疏类别准确率: 0.6354

1122/未知 515s 459ms/step - 损失: 0.9387 - 稀疏类别准确率: 0.6355

1123/未知 515s 459ms/step - 损失: 0.9385 - 稀疏类别准确率: 0.6355

1124/未知 516s 459ms/step - 损失: 0.9383 - 稀疏类别准确率: 0.6356

1125/未知 516s 459ms/step - 损失: 0.9381 - 稀疏类别准确率: 0.6356

1126/未知 517s 458ms/step - 损失: 0.9379 - 稀疏类别准确率: 0.6357

1127/未知 517s 458ms/step - 损失: 0.9378 - 稀疏类别准确率: 0.6357

1128/未知 518s 458ms/step - 损失: 0.9376 - 稀疏类别准确率: 0.6358

1129/未知 518s 458ms/step - 损失: 0.9374 - 稀疏类别准确率: 0.6358

1130/未知 519s 458ms/step - 损失: 0.9372 - 稀疏类别准确率: 0.6359

1131/未知 519s 458ms/step - 损失: 0.9371 - 稀疏类别准确率: 0.6360

1132/未知 519s 458ms/step - 损失: 0.9369 - 稀疏类别准确率: 0.6360

1133/未知 520s 458ms/step - 损失: 0.9367 - 稀疏类别准确率: 0.6361

1134/未知 520s 458ms/step - 损失: 0.9365 - 稀疏类别准确率: 0.6361

1135/未知 521s 458ms/step - 损失: 0.9364 - 稀疏类别准确率: 0.6362

1136/未知 521s 458ms/step - 损失: 0.9362 - 稀疏类别准确率: 0.6362

1137/未知 522s 458ms/step - 损失: 0.9360 - 稀疏类别准确率: 0.6363

1138/未知 522s 458ms/step - 损失: 0.9358 - 稀疏类别准确率: 0.6363

1139/未知 523s 458ms/step - 损失: 0.9356 - 稀疏类别准确率: 0.6364

1140/未知 523s 458ms/step - 损失: 0.9355 - 稀疏类别准确率: 0.6364

1141/未知 524s 458ms/step - 损失: 0.9353 - 稀疏类别准确率: 0.6365

1142/未知 524s 458ms/step - 损失: 0.9351 - 稀疏类别准确率: 0.6366

1143/未知 525s 458ms/step - 损失: 0.9350 - 稀疏类别准确率: 0.6366

1144/未知 525s 458ms/step - 损失: 0.9348 - 稀疏类别准确率: 0.6367

1145/未知 525s 458ms/step - 损失: 0.9346 - 稀疏类别准确率: 0.6367

1146/未知 526s 458ms/step - 损失: 0.9344 - 稀疏类别准确率: 0.6368

1147/未知 526s 458ms/step - 损失: 0.9343 - 稀疏类别准确率: 0.6368

1148/未知 527s 458ms/step - 损失: 0.9341 - 稀疏类别准确率: 0.6369

1149/未知 527s 458ms/step - 损失: 0.9339 - 稀疏类别准确率: 0.6369

1150/未知 528s 458ms/step - 损失: 0.9337 - 稀疏类别准确率: 0.6370

1151/未知 528s 458ms/step - 损失: 0.9336 - 稀疏类别准确率: 0.6370

1152/未知 528s 458ms/step - 损失: 0.9334 - 稀疏类别准确率: 0.6371

1153/未知 529s 458ms/step - 损失: 0.9332 - 稀疏类别准确率: 0.6372

1154/未知 529s 458ms/step - 损失: 0.9330 - 稀疏类别准确率: 0.6372

1155/未知 530s 458ms/step - 损失: 0.9329 - 稀疏类别准确率: 0.6373

1156/未知 530s 458ms/step - 损失: 0.9327 - 稀疏类别准确率: 0.6373

1157/未知 530s 458ms/step - 损失: 0.9325 - 稀疏类别准确率: 0.6374

1158/未知 531s 458ms/step - 损失: 0.9324 - 稀疏类别准确率: 0.6374

1159/未知 531s 458ms/step - 损失: 0.9322 - 稀疏类别准确率: 0.6375

1160/未知 532s 458ms/step - 损失: 0.9320 - 稀疏类别准确率: 0.6375

1161/未知 532s 458ms/step - 损失: 0.9318 - 稀疏类别准确率: 0.6376

1162/未知 532s 458ms/step - 损失: 0.9317 - 稀疏类别准确率: 0.6376

1163/未知 533s 458ms/step - 损失: 0.9315 - 稀疏类别准确率: 0.6377

1164/未知 533s 458ms/step - 损失: 0.9313 - 稀疏类别准确率: 0.6377

1165/未知 534s 458ms/step - 损失: 0.9312 - 稀疏类别准确率: 0.6378

1166/未知 534s 458ms/step - 损失: 0.9310 - 稀疏类别准确率: 0.6378

1167/未知 535s 458ms/step - 损失: 0.9308 - 稀疏类别准确率: 0.6379

1168/未知 535s 458ms/step - 损失: 0.9307 - 稀疏类别准确率: 0.6380

1169/未知 536s 458ms/step - 损失: 0.9305 - 稀疏类别准确率: 0.6380

1170/未知 536s 458ms/step - 损失: 0.9303 - 稀疏类别准确率: 0.6381

1171/未知 537s 458ms/step - 损失: 0.9302 - 稀疏类别准确率: 0.6381

1172/未知 537s 458ms/step - 损失: 0.9300 - 稀疏类别准确率: 0.6382

1173/未知 538s 458ms/step - 损失: 0.9298 - 稀疏类别准确率: 0.6382

1174/未知 538s 458ms/step - 损失: 0.9297 - 稀疏类别准确率: 0.6383

1175/未知 538s 458ms/step - 损失: 0.9295 - 稀疏类别准确率: 0.6383

1176/未知 539s 458ms/step - 损失: 0.9293 - 稀疏类别准确率: 0.6384

1177/未知 539s 458ms/step - 损失: 0.9292 - 稀疏类别准确率: 0.6384

1178/未知 540s 458ms/step - 损失: 0.9290 - 稀疏类别准确率: 0.6385

1179/未知 540s 458ms/step - 损失: 0.9288 - 稀疏类别准确率: 0.6385

1180/未知 541s 458ms/step - 损失: 0.9287 - 稀疏类别准确率: 0.6386

1181/未知 541s 458ms/step - 损失: 0.9285 - 稀疏类别准确率: 0.6386

1182/未知 542s 458ms/step - 损失: 0.9283 - 稀疏类别准确率: 0.6387

1183/未知 542s 458ms/step - 损失: 0.9282 - 稀疏类别准确率: 0.6387

1184/未知 543s 458ms/step - 损失: 0.9280 - 稀疏类别准确率: 0.6388

1185/未知 543s 458ms/step - 损失: 0.9278 - 稀疏类别准确率: 0.6388

1186/未知 543s 458ms/step - 损失: 0.9277 - 稀疏类别准确率: 0.6389

1187/未知 544s 458ms/step - 损失: 0.9275 - 稀疏类别准确率: 0.6389

1188/未知 544s 458ms/step - 损失: 0.9273 - 稀疏类别准确率: 0.6390

1189/未知 545s 458ms/step - 损失: 0.9272 - 稀疏类别准确率: 0.6390

1190/未知 545s 458ms/step - 损失: 0.9270 - 稀疏类别准确率: 0.6391

1191/未知 546s 458ms/step - 损失: 0.9268 - 稀疏类别准确率: 0.6391

1192/未知 546s 458ms/step - 损失: 0.9267 - 稀疏类别准确率: 0.6392

1193/未知 547s 458ms/step - 损失: 0.9265 - 稀疏类别准确率: 0.6392

1194/未知 547s 458ms/step - 损失: 0.9263 - 稀疏类别准确率: 0.6393

1195/未知 548s 458ms/step - 损失: 0.9262 - 稀疏类别准确率: 0.6394

1196/未知 548s 458ms/step - 损失: 0.9260 - 稀疏类别准确率: 0.6394

1197/未知 548s 458ms/step - 损失: 0.9259 - 稀疏类别准确率: 0.6395

1198/未知 549s 458ms/step - 损失: 0.9257 - 稀疏类别准确率: 0.6395

1199/未知 549s 458ms/step - 损失: 0.9255 - 稀疏类别准确率: 0.6396

1200/未知 550s 458ms/step - 损失: 0.9254 - 稀疏类别准确率: 0.6396

1201/未知 550s 458ms/step - 损失: 0.9252 - 稀疏类别准确率: 0.6397

1202/未知 551s 458ms/step - 损失: 0.9250 - 稀疏类别准确率: 0.6397

1203/未知 551s 458ms/step - 损失: 0.9249 - 稀疏类别准确率: 0.6398

1204/未知 552s 458ms/step - 损失: 0.9247 - 稀疏类别准确率: 0.6398

1205/未知 552s 458ms/step - 损失: 0.9246 - 稀疏类别准确率: 0.6399

1206/未知 553s 458ms/step - 损失: 0.9244 - 稀疏类别准确率: 0.6399

1207/未知 553s 458ms/step - 损失: 0.9242 - 稀疏类别准确率: 0.6400

1208/未知 554s 458ms/step - 损失: 0.9241 - 稀疏类别准确率: 0.6400

1209/未知 554s 458ms/step - 损失: 0.9239 - 稀疏类别准确率: 0.6401

1210/未知 555s 458ms/step - 损失: 0.9238 - 稀疏类别准确率: 0.6401

1211/未知 555s 458ms/step - 损失: 0.9236 - 稀疏类别准确率: 0.6402

1212/未知 556s 458ms/step - 损失: 0.9234 - 稀疏类别准确率: 0.6402

1213/未知 556s 458ms/step - 损失: 0.9233 - 稀疏类别准确率: 0.6403

1214/未知 557s 458ms/step - 损失: 0.9231 - 稀疏类别准确率: 0.6403

1215/未知 557s 458ms/step - 损失: 0.9230 - 稀疏类别准确率: 0.6404

1216/未知 558s 458ms/step - 损失: 0.9228 - 稀疏类别准确率: 0.6404

1217/未知 558s 458ms/step - 损失: 0.9226 - 稀疏类别准确率: 0.6405

1218/未知 559s 458ms/step - 损失: 0.9225 - 稀疏类别准确率: 0.6405

1219/未知 559s 458ms/step - 损失: 0.9223 - 稀疏类别准确率: 0.6406

1220/未知 560s 458ms/step - 损失: 0.9222 - 稀疏类别准确率: 0.6406

1221/未知 560s 458ms/step - 损失: 0.9220 - 稀疏类别准确率: 0.6407

1222/未知 560s 458ms/step - 损失: 0.9218 - 稀疏类别准确率: 0.6407

1223/未知 561s 458ms/step - 损失: 0.9217 - 稀疏类别准确率: 0.6408

1224/未知 561s 458ms/step - 损失: 0.9215 - 稀疏类别准确率: 0.6408

1225/未知 562s 458ms/step - 损失: 0.9214 - 稀疏类别准确率: 0.6409

1226/未知 562s 458ms/step - 损失: 0.9212 - 稀疏类别准确率: 0.6409

1227/未知 563s 458ms/step - 损失: 0.9211 - 稀疏类别准确率: 0.6410

1228/未知 563s 458ms/step - 损失: 0.9209 - 稀疏类别准确率: 0.6410

1229/未知 564s 458ms/step - 损失: 0.9207 - 稀疏类别准确率: 0.6410

1230/未知 564s 458ms/step - 损失: 0.9206 - 稀疏类别准确率: 0.6411

1231/未知 565s 458ms/step - 损失: 0.9204 - 稀疏类别准确率: 0.6411

1232/未知 565s 458ms/step - 损失: 0.9203 - 稀疏类别准确率: 0.6412

1233/未知 566s 458ms/step - 损失: 0.9201 - 稀疏类别准确率: 0.6412

1234/未知 566s 458ms/step - 损失: 0.9200 - 稀疏类别准确率: 0.6413

1235/未知 567s 458ms/step - 损失: 0.9198 - 稀疏类别准确率: 0.6413

1236/未知 567s 458ms/step - 损失: 0.9197 - 稀疏类别准确率: 0.6414

1237/未知 568s 458ms/step - 损失: 0.9195 - 稀疏类别准确率: 0.6414

1238/未知 568s 458ms/step - 损失: 0.9193 - 稀疏类别准确率: 0.6415

1239/未知 569s 458ms/step - 损失: 0.9192 - 稀疏类别准确率: 0.6415

1240/未知 569s 458ms/step - 损失: 0.9190 - 稀疏类别准确率: 0.6416

1241/未知 569s 458ms/step - 损失: 0.9189 - 稀疏类别准确率: 0.6416

1242/未知 570s 458ms/step - 损失: 0.9187 - 稀疏类别准确率: 0.6417

1243/未知 570s 458ms/step - 损失: 0.9186 - 稀疏类别准确率: 0.6417

1244/未知 571s 458ms/step - 损失: 0.9184 - 稀疏类别准确率: 0.6418

1245/未知 571s 458ms/step - 损失: 0.9183 - 稀疏类别准确率: 0.6418

1246/未知 572s 458ms/step - 损失: 0.9181 - 稀疏类别准确率: 0.6419

1247/未知 572s 458ms/step - 损失: 0.9180 - 稀疏类别准确率: 0.6419

1248/未知 573s 458ms/step - 损失: 0.9178 - 稀疏类别准确率: 0.6420

1249/未知 573s 458ms/step - 损失: 0.9177 - 稀疏类别准确率: 0.6420

1250/未知 574s 458ms/step - 损失: 0.9175 - 稀疏类别准确率: 0.6421

1251/未知 574s 458ms/step - 损失: 0.9173 - 稀疏类别准确率: 0.6421

1252/未知 574s 458ms/step - 损失: 0.9172 - 稀疏类别准确率: 0.6422

1253/未知 575s 458ms/step - 损失: 0.9170 - 稀疏类别准确率: 0.6422

1254/未知 575s 458ms/step - 损失: 0.9169 - 稀疏类别准确率: 0.6423

1255/未知 576s 458ms/step - 损失: 0.9167 - 稀疏类别准确率: 0.6423

1256/未知 576s 458ms/step - 损失: 0.9166 - 稀疏类别准确率: 0.6424

1257/未知 577s 458ms/step - 损失: 0.9164 - 稀疏类别准确率: 0.6424

1258/未知 577s 458ms/step - 损失: 0.9163 - 稀疏类别准确率: 0.6424

1259/未知 578s 458ms/step - 损失: 0.9161 - 稀疏类别准确率: 0.6425

1260/未知 578s 459ms/step - 损失: 0.9160 - 稀疏类别准确率: 0.6425

1261/未知 579s 459ms/step - 损失: 0.9158 - 稀疏类别准确率: 0.6426

1262/未知 579s 458ms/step - 损失: 0.9157 - 稀疏类别准确率: 0.6426

1263/未知 580s 459ms/step - 损失: 0.9155 - 稀疏类别准确率: 0.6427

1264/未知 580s 459ms/step - 损失: 0.9154 - 稀疏类别准确率: 0.6427

1265/未知 581s 459ms/step - 损失: 0.9152 - 稀疏类别准确率: 0.6428

1266/未知 581s 459ms/step - 损失: 0.9151 - 稀疏类别准确率: 0.6428

1267/未知 582s 459ms/step - 损失: 0.9149 - 稀疏类别准确率: 0.6429

1268/未知 582s 459ms/step - 损失: 0.9148 - 稀疏类别准确率: 0.6429

1269/未知 583s 459ms/step - 损失: 0.9146 - 稀疏类别准确率: 0.6430

1270/未知 583s 459ms/step - 损失: 0.9145 - 稀疏类别准确率: 0.6430

1271/未知 584s 459ms/step - 损失: 0.9143 - 稀疏类别准确率: 0.6431

1272/未知 584s 459ms/step - 损失: 0.9142 - 稀疏类别准确率: 0.6431

1273/未知 584s 459ms/step - 损失: 0.9140 - 稀疏类别准确率: 0.6432

1274/未知 585s 459ms/step - 损失: 0.9139 - 稀疏类别准确率: 0.6432

1275/未知 585s 459ms/step - 损失: 0.9137 - 稀疏类别准确率: 0.6432

1276/未知 586s 459ms/step - 损失: 0.9136 - 稀疏类别准确率: 0.6433

1277/未知 586s 459ms/step - 损失: 0.9134 - 稀疏类别准确率: 0.6433

1278/未知 587s 459ms/step - 损失: 0.9133 - 稀疏类别准确率: 0.6434

1279/未知 587s 459ms/step - 损失: 0.9131 - 稀疏类别准确率: 0.6434

1280/未知 588s 458ms/step - 损失: 0.9130 - 稀疏类别准确率: 0.6435

1281/未知 588s 458ms/step - 损失: 0.9128 - 稀疏类别准确率: 0.6435

1282/未知 589s 458ms/step - 损失: 0.9127 - 稀疏类别准确率: 0.6436

1283/未知 589s 458ms/step - 损失: 0.9126 - 稀疏类别准确率: 0.6436

1284/未知 589s 459ms/step - 损失: 0.9124 - 稀疏类别准确率: 0.6437

1285/未知 590s 458ms/step - 损失: 0.9123 - 稀疏类别准确率: 0.6437

1286/未知 590s 458ms/step - 损失: 0.9121 - 稀疏类别准确率: 0.6438

1287/未知 591s 458ms/step - 损失: 0.9120 - 稀疏类别准确率: 0.6438

1288/未知 591s 458ms/step - 损失: 0.9118 - 稀疏类别准确率: 0.6438

1289/未知 591s 458ms/step - 损失: 0.9117 - 稀疏类别准确率: 0.6439

1290/未知 592s 458ms/step - 损失: 0.9115 - 稀疏类别准确率: 0.6439

1291/未知 592s 458ms/step - 损失: 0.9114 - 稀疏类别准确率: 0.6440

1292/未知 593s 458ms/step - 损失: 0.9112 - 稀疏类别准确率: 0.6440

1293/未知 593s 458ms/step - 损失: 0.9111 - 稀疏类别准确率: 0.6441

1294/未知 594s 458ms/step - 损失: 0.9109 - 稀疏类别准确率: 0.6441

1295/未知 594s 458ms/step - 损失: 0.9108 - 稀疏类别准确率: 0.6442

1296/未知 595s 458ms/step - 损失: 0.9107 - 稀疏类别准确率: 0.6442

1297/未知 595s 458ms/step - 损失: 0.9105 - 稀疏类别准确率: 0.6443

1298/未知 596s 458ms/step - 损失: 0.9104 - 稀疏类别准确率: 0.6443

1299/未知 596s 458ms/step - 损失: 0.9102 - 稀疏类别准确率: 0.6443

1300/未知 596s 458ms/step - 损失: 0.9101 - 稀疏类别准确率: 0.6444

1301/未知 597s 458ms/step - 损失: 0.9099 - 稀疏类别准确率: 0.6444

1302/未知 597s 458ms/step - 损失: 0.9098 - 稀疏类别准确率: 0.6445

1303/未知 598s 458ms/step - 损失: 0.9096 - 稀疏类别准确率: 0.6445

1304/未知 598s 458ms/step - 损失: 0.9095 - 稀疏类别准确率: 0.6446

1305/未知 599s 458ms/step - 损失: 0.9094 - 稀疏类别准确率: 0.6446

1306/未知 599s 458ms/step - 损失: 0.9092 - 稀疏类别准确率: 0.6447

1307/未知 600s 458ms/step - 损失: 0.9091 - 稀疏类别准确率: 0.6447

1308/未知 600s 458ms/step - 损失: 0.9089 - 稀疏类别准确率: 0.6448

1309/未知 601s 458ms/step - 损失: 0.9088 - 稀疏类别准确率: 0.6448

1310/未知 601s 458ms/step - 损失: 0.9086 - 稀疏类别准确率: 0.6448

1311/未知 602s 458ms/step - 损失: 0.9085 - 稀疏类别准确率: 0.6449

1312/未知 602s 458ms/step - 损失: 0.9084 - 稀疏类别准确率: 0.6449

1313/未知 602s 458ms/step - 损失: 0.9082 - 稀疏类别准确率: 0.6450

1314/未知 603s 458ms/step - 损失: 0.9081 - 稀疏类别准确率: 0.6450

1315/未知 603s 458ms/step - 损失: 0.9079 - 稀疏类别准确率: 0.6451

1316/未知 604s 458ms/step - 损失: 0.9078 - 稀疏类别准确率: 0.6451

1317/未知 604s 458ms/step - 损失: 0.9076 - 稀疏类别准确率: 0.6452

1318/未知 604s 458ms/step - 损失: 0.9075 - 稀疏类别准确率: 0.6452

1319/未知 605s 458ms/step - 损失: 0.9074 - 稀疏类别准确率: 0.6452

1320/未知 605s 458ms/step - 损失: 0.9072 - 稀疏类别准确率: 0.6453

1321/未知 605s 458ms/step - 损失: 0.9071 - 稀疏类别准确率: 0.6453

1322/未知 606s 458ms/step - 损失: 0.9069 - 稀疏类别准确率: 0.6454

1323/未知 606s 458ms/step - 损失: 0.9068 - 稀疏类别准确率: 0.6454

1324/未知 607s 458ms/step - 损失: 0.9067 - 稀疏类别准确率: 0.6455

1325/未知 607s 458ms/step - 损失: 0.9065 - 稀疏类别准确率: 0.6455

1326/未知 608s 458ms/step - 损失: 0.9064 - 稀疏类别准确率: 0.6455

1327/未知 608s 458ms/step - 损失: 0.9062 - 稀疏类别准确率: 0.6456

1328/未知 609s 458ms/step - 损失: 0.9061 - 稀疏类别准确率: 0.6456

1329/未知 609s 458ms/step - 损失: 0.9060 - 稀疏类别准确率: 0.6457

1330/未知 609s 458ms/step - 损失: 0.9058 - 稀疏类别准确率: 0.6457

1331/未知 610s 458ms/step - 损失: 0.9057 - 稀疏类别准确率: 0.6458

1332/未知 610s 458ms/step - 损失: 0.9055 - 稀疏类别准确率: 0.6458

1333/未知 611s 458ms/step - 损失: 0.9054 - 稀疏类别准确率: 0.6459

1334/未知 611s 458ms/step - 损失: 0.9053 - 稀疏类别准确率: 0.6459

1335/未知 612s 458ms/step - 损失: 0.9051 - 稀疏类别准确率: 0.6459

1336/未知 612s 458ms/step - 损失: 0.9050 - 稀疏类别准确率: 0.6460

1337/未知 613s 458ms/step - 损失: 0.9048 - 稀疏类别准确率: 0.6460

1338/未知 613s 458ms/step - 损失: 0.9047 - 稀疏类别准确率: 0.6461

1339/未知 614s 458ms/step - 损失: 0.9046 - 稀疏类别准确率: 0.6461

1340/未知 614s 458ms/step - 损失: 0.9044 - 稀疏类别准确率: 0.6462

1341/未知 614s 458ms/step - 损失: 0.9043 - 稀疏类别准确率: 0.6462

1342/未知 615s 458ms/step - 损失: 0.9042 - 稀疏类别准确率: 0.6462

1343/未知 615s 458ms/step - 损失: 0.9040 - 稀疏类别准确率: 0.6463

1344/未知 615s 458ms/step - 损失: 0.9039 - 稀疏类别准确率: 0.6463

1345/未知 616s 458ms/step - 损失: 0.9037 - 稀疏类别准确率: 0.6464

1346/未知 616s 458ms/step - 损失: 0.9036 - 稀疏类别准确率: 0.6464

1347/未知 617s 457ms/step - 损失: 0.9035 - 稀疏类别准确率: 0.6465

1348/未知 617s 457ms/step - 损失: 0.9033 - 稀疏类别准确率: 0.6465

1349/未知 618s 457ms/step - 损失: 0.9032 - 稀疏类别准确率: 0.6465

1350/未知 618s 457ms/step - 损失: 0.9031 - 稀疏类别准确率: 0.6466

1351/未知 618s 457ms/step - 损失: 0.9029 - 稀疏类别准确率: 0.6466

1352/未知 619s 457ms/step - 损失: 0.9028 - 稀疏类别准确率: 0.6467

1353/未知 619s 457ms/step - 损失: 0.9026 - 稀疏类别准确率: 0.6467

1354/未知 620s 457ms/step - 损失: 0.9025 - 稀疏类别准确率: 0.6468

1355/未知 620s 457ms/step - 损失: 0.9024 - 稀疏类别准确率: 0.6468

1356/未知 621s 457ms/step - 损失: 0.9022 - 稀疏类别准确率: 0.6468

1357/未知 621s 457ms/step - 损失: 0.9021 - 稀疏类别准确率: 0.6469

1358/未知 622s 457ms/step - 损失: 0.9020 - 稀疏类别准确率: 0.6469

1359/未知 622s 457ms/step - 损失: 0.9018 - 稀疏类别准确率: 0.6470

1360/未知 623s 457ms/step - 损失: 0.9017 - 稀疏类别准确率: 0.6470

1361/未知 623s 457ms/step - 损失: 0.9016 - 稀疏类别准确率: 0.6471

1362/未知 624s 457ms/step - 损失: 0.9014 - 稀疏类别准确率: 0.6471

1363/未知 624s 457ms/step - 损失: 0.9013 - 稀疏类别准确率: 0.6471

1364/未知 624s 457ms/step - 损失: 0.9012 - 稀疏类别准确率: 0.6472

1365/未知 625s 457ms/step - 损失: 0.9010 - 稀疏类别准确率: 0.6472

1366/未知 625s 457ms/step - 损失: 0.9009 - 稀疏类别准确率: 0.6473

1367/未知 625s 457ms/step - 损失: 0.9008 - 稀疏类别准确率: 0.6473

1368/未知 626s 457ms/step - 损失: 0.9006 - 稀疏类别准确率: 0.6474

1369/未知 626s 457ms/step - 损失: 0.9005 - 稀疏类别准确率: 0.6474

1370/未知 627s 457ms/step - 损失: 0.9004 - 稀疏类别准确率: 0.6474

1371/未知 627s 457ms/step - 损失: 0.9002 - 稀疏类别准确率: 0.6475

1372/未知 627s 457ms/step - 损失: 0.9001 - 稀疏类别准确率: 0.6475

1373/未知 628s 457ms/step - 损失: 0.9000 - 稀疏类别准确率: 0.6476

1374/未知 628s 457ms/step - 损失: 0.8998 - 稀疏类别准确率: 0.6476

1375/未知 629s 457ms/step - 损失: 0.8997 - 稀疏类别准确率: 0.6476

1376/未知 629s 457ms/step - 损失: 0.8996 - 稀疏类别准确率: 0.6477

1377/未知 630s 457ms/step - 损失: 0.8994 - 稀疏类别准确率: 0.6477

1378/未知 630s 457ms/step - 损失: 0.8993 - 稀疏类别准确率: 0.6478

1379/未知 631s 457ms/step - 损失: 0.8992 - 稀疏类别准确率: 0.6478

1380/未知 631s 457ms/step - 损失: 0.8990 - 稀疏类别准确率: 0.6479

1381/未知 632s 457ms/step - 损失: 0.8989 - 稀疏类别准确率: 0.6479

1382/未知 632s 457ms/step - 损失: 0.8988 - 稀疏类别准确率: 0.6479

1383/未知 633s 457ms/step - 损失: 0.8986 - 稀疏类别准确率: 0.6480

1384/未知 633s 457ms/step - 损失: 0.8985 - 稀疏类别准确率: 0.6480

1385/未知 633s 457ms/step - 损失: 0.8984 - 稀疏类别准确率: 0.6481

1386/未知 634s 457ms/step - 损失: 0.8982 - 稀疏类别准确率: 0.6481

1387/未知 634s 457ms/step - 损失: 0.8981 - 稀疏类别准确率: 0.6481

1388/未知 634s 457ms/step - 损失: 0.8980 - 稀疏类别准确率: 0.6482

1389/未知 635s 457ms/step - 损失: 0.8978 - 稀疏类别准确率: 0.6482

1390/未知 635s 457ms/step - 损失: 0.8977 - 稀疏类别准确率: 0.6483

1391/未知 636s 457ms/step - 损失: 0.8976 - 稀疏类别准确率: 0.6483

1392/未知 636s 457ms/step - 损失: 0.8974 - 稀疏类别准确率: 0.6483

1393/未知 636s 456ms/step - 损失: 0.8973 - 稀疏类别准确率: 0.6484

1394/未知 637s 456ms/step - 损失: 0.8972 - 稀疏类别准确率: 0.6484

1395/未知 637s 456ms/step - 损失: 0.8971 - 稀疏类别准确率: 0.6485

1396/未知 638s 456ms/step - 损失: 0.8969 - 稀疏类别准确率: 0.6485

1397/未知 638s 456ms/step - 损失: 0.8968 - 稀疏类别准确率: 0.6485

1398/未知 639s 456ms/step - 损失: 0.8967 - 稀疏类别准确率: 0.6486

1399/未知 639s 456ms/step - 损失: 0.8965 - 稀疏类别准确率: 0.6486

1400/未知 640s 456ms/step - 损失: 0.8964 - 稀疏类别准确率: 0.6487

1401/未知 640s 456ms/step - 损失: 0.8963 - 稀疏类别准确率: 0.6487

1402/未知 640s 456ms/step - 损失: 0.8962 - 稀疏类别准确率: 0.6488

1403/未知 641s 456ms/step - 损失: 0.8960 - 稀疏类别准确率: 0.6488

1404/未知 641s 456ms/step - 损失: 0.8959 - 稀疏类别准确率: 0.6488

1405/未知 642s 456ms/step - 损失: 0.8958 - 稀疏类别准确率: 0.6489

1406/未知 642s 456ms/step - 损失: 0.8956 - 稀疏类别准确率: 0.6489

1407/未知 643s 456ms/step - 损失: 0.8955 - 稀疏类别准确率: 0.6490

1408/未知 643s 456ms/step - 损失: 0.8954 - 稀疏类别准确率: 0.6490

1409/未知 644s 457ms/step - 损失: 0.8953 - 稀疏类别准确率: 0.6490

1410/未知 644s 457ms/step - 损失: 0.8951 - 稀疏类别准确率: 0.6491

1411/未知 645s 457ms/step - 损失: 0.8950 - 稀疏类别准确率: 0.6491

1412/未知 645s 457ms/step - 损失: 0.8949 - 稀疏类别准确率: 0.6492

1413/未知 646s 457ms/step - 损失: 0.8947 - 稀疏类别准确率: 0.6492

1414/未知 646s 457ms/step - 损失: 0.8946 - 稀疏类别准确率: 0.6492

1415/未知 647s 457ms/step - 损失: 0.8945 - 稀疏类别准确率: 0.6493

1416/未知 647s 457ms/step - 损失: 0.8944 - 稀疏类别准确率: 0.6493

1417/未知 647s 457ms/step - 损失: 0.8942 - 稀疏类别准确率: 0.6494

1418/未知 648s 457ms/step - 损失: 0.8941 - 稀疏类别准确率: 0.6494

1419/未知 648s 457ms/step - 损失: 0.8940 - 稀疏类别准确率: 0.6494

1420/未知 649s 456ms/step - 损失: 0.8939 - 稀疏类别准确率: 0.6495

1421/未知 649s 456ms/step - 损失: 0.8937 - 稀疏类别准确率: 0.6495

1422/未知 650s 456ms/step - 损失: 0.8936 - 稀疏类别准确率: 0.6495

1423/未知 650s 456ms/step - 损失: 0.8935 - 稀疏类别准确率: 0.6496

1424/未知 651s 456ms/step - 损失: 0.8933 - 稀疏类别准确率: 0.6496

1425/未知 651s 456ms/step - 损失: 0.8932 - 稀疏类别准确率: 0.6497

1426/未知 651s 456ms/step - 损失: 0.8931 - 稀疏类别准确率: 0.6497

1427/未知 652s 456ms/step - 损失: 0.8930 - 稀疏类别准确率: 0.6497

1428/未知 652s 456ms/step - 损失: 0.8928 - 稀疏类别准确率: 0.6498

1429/未知 653s 456ms/step - 损失: 0.8927 - 稀疏类别准确率: 0.6498

1430/未知 653s 456ms/step - 损失: 0.8926 - 稀疏类别准确率: 0.6499

1431/未知 653s 456ms/step - 损失: 0.8925 - 稀疏类别准确率: 0.6499

1432/未知 654s 456ms/step - 损失: 0.8923 - 稀疏类别准确率: 0.6499

1433/未知 654s 456ms/step - 损失: 0.8922 - 稀疏类别准确率: 0.6500

1434/未知 655s 456ms/step - 损失: 0.8921 - 稀疏类别准确率: 0.6500

1435/未知 655s 456ms/step - 损失: 0.8920 - 稀疏类别准确率: 0.6501

1436/未知 655s 456ms/step - 损失: 0.8918 - 稀疏类别准确率: 0.6501

1437/未知 656s 456ms/step - 损失: 0.8917 - 稀疏类别准确率: 0.6501

1438/未知 656s 456ms/step - 损失: 0.8916 - 稀疏类别准确率: 0.6502

1439/未知 657s 456ms/step - 损失: 0.8915 - 稀疏类别准确率: 0.6502

1440/未知 657s 456ms/step - 损失: 0.8913 - 稀疏类别准确率: 0.6503

1441/未知 657s 456ms/step - 损失: 0.8912 - 稀疏类别准确率: 0.6503

1442/未知 658s 456ms/step - 损失: 0.8911 - 稀疏类别准确率: 0.6503

1443/未知 658s 456ms/step - 损失: 0.8910 - 稀疏类别准确率: 0.6504

1444/未知 659s 456ms/step - 损失: 0.8909 - 稀疏类别准确率: 0.6504

1445/未知 659s 456ms/step - 损失: 0.8907 - 稀疏类别准确率: 0.6504

1446/未知 660s 456ms/step - 损失: 0.8906 - 稀疏类别准确率: 0.6505

1447/未知 660s 456ms/step - 损失: 0.8905 - 稀疏类别准确率: 0.6505

1448/未知 661s 456ms/step - 损失: 0.8904 - 稀疏类别准确率: 0.6506

1449/未知 661s 456ms/step - 损失: 0.8902 - 稀疏类别准确率: 0.6506

1450/未知 662s 456ms/step - 损失: 0.8901 - 稀疏类别准确率: 0.6506

1451/未知 662s 456ms/step - 损失: 0.8900 - 稀疏类别准确率: 0.6507

1452/未知 662s 456ms/step - 损失: 0.8899 - 稀疏类别准确率: 0.6507

1453/未知 663s 456ms/step - 损失: 0.8897 - 稀疏类别准确率: 0.6508

1454/未知 663s 456ms/step - 损失: 0.8896 - 稀疏类别准确率: 0.6508

1455/未知 664s 456ms/step - 损失: 0.8895 - 稀疏类别准确率: 0.6508

1456/未知 664s 456ms/step - 损失: 0.8894 - 稀疏类别准确率: 0.6509

1457/未知 665s 456ms/step - 损失: 0.8893 - 稀疏类别准确率: 0.6509

1458/未知 665s 456ms/step - 损失: 0.8891 - 稀疏类别准确率: 0.6509

1459/未知 665s 456ms/step - 损失: 0.8890 - 稀疏类别准确率: 0.6510

1460/未知 666s 456ms/step - 损失: 0.8889 - 稀疏类别准确率: 0.6510

1461/未知 666s 456ms/step - 损失: 0.8888 - 稀疏类别准确率: 0.6511

1462/未知 667s 456ms/step - 损失: 0.8887 - 稀疏类别准确率: 0.6511

1463/未知 667s 455ms/step - 损失: 0.8885 - 稀疏类别准确率: 0.6511

1464/未知 667s 455ms/step - 损失: 0.8884 - 稀疏类别准确率: 0.6512

1465/未知 668s 455ms/step - 损失: 0.8883 - 稀疏类别准确率: 0.6512

1466/未知 668s 455ms/step - 损失: 0.8882 - 稀疏类别准确率: 0.6512

1467/未知 669s 455ms/step - 损失: 0.8880 - 稀疏类别准确率: 0.6513

1468/未知 669s 455ms/step - 损失: 0.8879 - 稀疏类别准确率: 0.6513

1469/未知 669s 455ms/step - 损失: 0.8878 - 稀疏类别准确率: 0.6514

1470/未知 670s 455ms/step - 损失: 0.8877 - 稀疏类别准确率: 0.6514

1471/未知 670s 455ms/step - 损失: 0.8876 - 稀疏类别准确率: 0.6514

1472/未知 671s 455ms/step - 损失: 0.8874 - 稀疏类别准确率: 0.6515

1473/未知 671s 455ms/step - 损失: 0.8873 - 稀疏类别准确率: 0.6515

1474/未知 672s 455ms/step - 损失: 0.8872 - 稀疏类别准确率: 0.6515

1475/未知 672s 455ms/step - 损失: 0.8871 - 稀疏类别准确率: 0.6516

1476/未知 673s 455ms/step - 损失: 0.8870 - 稀疏类别准确率: 0.6516

1477/未知 673秒 455毫秒/步 - 损失: 0.8868 - 稀疏分类准确率: 0.6517

1478/未知 673秒 455毫秒/步 - 损失: 0.8867 - 稀疏分类准确率: 0.6517

1479/未知 674秒 455毫秒/步 - 损失: 0.8866 - 稀疏分类准确率: 0.6517

1480/未知 674秒 455毫秒/步 - 损失: 0.8865 - 稀疏分类准确率: 0.6518

1481/未知 674秒 455毫秒/步 - 损失: 0.8864 - 稀疏分类准确率: 0.6518

1482/未知 675秒 455毫秒/步 - 损失: 0.8863 - 稀疏分类准确率: 0.6518

1483/未知 675秒 455毫秒/步 - 损失: 0.8861 - 稀疏分类准确率: 0.6519

1484/未知 676秒 455毫秒/步 - 损失: 0.8860 - 稀疏分类准确率: 0.6519

1485/未知 676秒 455毫秒/步 - 损失: 0.8859 - 稀疏分类准确率: 0.6520

1486/未知 677秒 455毫秒/步 - 损失: 0.8858 - 稀疏分类准确率: 0.6520

1487/未知 677秒 455毫秒/步 - 损失: 0.8857 - 稀疏分类准确率: 0.6520

1488/未知 677秒 455毫秒/步 - 损失: 0.8855 - 稀疏分类准确率: 0.6521

1489/未知 678秒 455毫秒/步 - 损失: 0.8854 - 稀疏分类准确率: 0.6521

1490/未知 678秒 455毫秒/步 - 损失: 0.8853 - 稀疏分类准确率: 0.6521

1491/未知 679秒 455毫秒/步 - 损失: 0.8852 - 稀疏分类准确率: 0.6522

1492/未知 679秒 455毫秒/步 - 损失: 0.8851 - 稀疏分类准确率: 0.6522

1493/未知 679秒 455毫秒/步 - 损失: 0.8850 - 稀疏分类准确率: 0.6523

1494/未知 680秒 455毫秒/步 - 损失: 0.8848 - 稀疏分类准确率: 0.6523

1495/未知 680秒 455毫秒/步 - 损失: 0.8847 - 稀疏分类准确率: 0.6523

1496/未知 681秒 455毫秒/步 - 损失: 0.8846 - 稀疏分类准确率: 0.6524

1497/未知 681秒 455毫秒/步 - 损失: 0.8845 - 稀疏分类准确率: 0.6524

1498/未知 682秒 455毫秒/步 - 损失: 0.8844 - 稀疏分类准确率: 0.6524

1499/未知 682秒 455毫秒/步 - 损失: 0.8843 - 稀疏分类准确率: 0.6525

1500/未知 683秒 455毫秒/步 - 损失: 0.8841 - 稀疏分类准确率: 0.6525

1501/未知 683秒 455毫秒/步 - 损失: 0.8840 - 稀疏分类准确率: 0.6525

1502/未知 684秒 455毫秒/步 - 损失: 0.8839 - 稀疏分类准确率: 0.6526

1503/未知 684秒 455毫秒/步 - 损失: 0.8838 - 稀疏分类准确率: 0.6526

1504/未知 685秒 455毫秒/步 - 损失: 0.8837 - 稀疏分类准确率: 0.6527

1505/未知 685秒 455毫秒/步 - 损失: 0.8836 - 稀疏分类准确率: 0.6527

1506/未知 685秒 455毫秒/步 - 损失: 0.8834 - 稀疏分类准确率: 0.6527

1507/未知 686秒 455毫秒/步 - 损失: 0.8833 - 稀疏分类准确率: 0.6528

1508/未知 686秒 455毫秒/步 - 损失: 0.8832 - 稀疏分类准确率: 0.6528

1509/未知 687秒 455毫秒/步 - 损失: 0.8831 - 稀疏分类准确率: 0.6528

1510/未知 687秒 455毫秒/步 - 损失: 0.8830 - 稀疏分类准确率: 0.6529

1511/未知 687秒 455毫秒/步 - 损失: 0.8829 - 稀疏分类准确率: 0.6529

1512/未知 688秒 454毫秒/步 - 损失: 0.8827 - 稀疏分类准确率: 0.6529

1513/未知 688秒 454毫秒/步 - 损失: 0.8826 - 稀疏分类准确率: 0.6530

1514/未知 688秒 454毫秒/步 - 损失: 0.8825 - 稀疏分类准确率: 0.6530

1515/未知 689秒 454毫秒/步 - 损失: 0.8824 - 稀疏分类准确率: 0.6531

1516/未知 689秒 454毫秒/步 - 损失: 0.8823 - 稀疏分类准确率: 0.6531

1517/未知 690秒 454毫秒/步 - 损失: 0.8822 - 稀疏分类准确率: 0.6531

1518/未知 690秒 454毫秒/步 - 损失: 0.8821 - 稀疏分类准确率: 0.6532

1519/未知 690秒 454毫秒/步 - 损失: 0.8819 - 稀疏分类准确率: 0.6532

1520/未知 691秒 454毫秒/步 - 损失: 0.8818 - 稀疏分类准确率: 0.6532

1521/未知 691秒 454毫秒/步 - 损失: 0.8817 - 稀疏分类准确率: 0.6533

1522/未知 692秒 454毫秒/步 - 损失: 0.8816 - 稀疏分类准确率: 0.6533

1523/未知 692秒 454毫秒/步 - 损失: 0.8815 - 稀疏分类准确率: 0.6533

1524/未知 693秒 454毫秒/步 - 损失: 0.8814 - 稀疏分类准确率: 0.6534

1525/未知 693秒 454毫秒/步 - 损失: 0.8813 - 稀疏分类准确率: 0.6534

1526/未知 694秒 454毫秒/步 - 损失: 0.8811 - 稀疏分类准确率: 0.6534

1527/未知 694秒 454毫秒/步 - 损失: 0.8810 - 稀疏分类准确率: 0.6535

1528/未知 695秒 454毫秒/步 - 损失: 0.8809 - 稀疏分类准确率: 0.6535

1529/未知 695秒 454毫秒/步 - 损失: 0.8808 - 稀疏分类准确率: 0.6536

1530/未知 695秒 454毫秒/步 - 损失: 0.8807 - 稀疏分类准确率: 0.6536

1531/未知 696秒 454毫秒/步 - 损失: 0.8806 - 稀疏分类准确率: 0.6536

1532/未知 696秒 454毫秒/步 - 损失: 0.8805 - 稀疏分类准确率: 0.6537

1533/未知 697秒 454毫秒/步 - 损失: 0.8803 - 稀疏分类准确率: 0.6537

1534/未知 697秒 454毫秒/步 - 损失: 0.8802 - 稀疏分类准确率: 0.6537

1535/未知 697秒 454毫秒/步 - 损失: 0.8801 - 稀疏分类准确率: 0.6538

1536/未知 698秒 454毫秒/步 - 损失: 0.8800 - 稀疏分类准确率: 0.6538

1537/未知 698秒 454毫秒/步 - 损失: 0.8799 - 稀疏分类准确率: 0.6538

1538/未知 699秒 454毫秒/步 - 损失: 0.8798 - 稀疏分类准确率: 0.6539

1539/未知 699秒 454毫秒/步 - 损失: 0.8797 - 稀疏分类准确率: 0.6539

1540/未知 699秒 454毫秒/步 - 损失: 0.8796 - 稀疏分类准确率: 0.6539

1541/未知 700秒 454毫秒/步 - 损失: 0.8794 - 稀疏分类准确率: 0.6540

1542/未知 700秒 454毫秒/步 - 损失: 0.8793 - 稀疏分类准确率: 0.6540

1543/未知 701秒 454毫秒/步 - 损失: 0.8792 - 稀疏分类准确率: 0.6540

1544/未知 701秒 454毫秒/步 - 损失: 0.8791 - 稀疏分类准确率: 0.6541

1545/未知 702秒 454毫秒/步 - 损失: 0.8790 - 稀疏分类准确率: 0.6541

1546/未知 702秒 454毫秒/步 - 损失: 0.8789 - 稀疏分类准确率: 0.6542

1547/未知 702秒 454毫秒/步 - 损失: 0.8788 - 稀疏分类准确率: 0.6542

1548/未知 703秒 454毫秒/步 - 损失: 0.8787 - 稀疏分类准确率: 0.6542

1549/未知 703秒 454毫秒/步 - 损失: 0.8786 - 稀疏分类准确率: 0.6543

1550/未知 704秒 454毫秒/步 - 损失: 0.8784 - 稀疏分类准确率: 0.6543

1551/未知 704秒 454毫秒/步 - 损失: 0.8783 - 稀疏分类准确率: 0.6543

1552/未知 705秒 454毫秒/步 - 损失: 0.8782 - 稀疏分类准确率: 0.6544

1553/未知 705秒 454毫秒/步 - 损失: 0.8781 - 稀疏分类准确率: 0.6544

1554/未知 705秒 454毫秒/步 - 损失: 0.8780 - 稀疏分类准确率: 0.6544

1555/未知 706秒 453毫秒/步 - 损失: 0.8779 - 稀疏分类准确率: 0.6545

1556/未知 706秒 453毫秒/步 - 损失: 0.8778 - 稀疏分类准确率: 0.6545

1557/未知 706秒 453毫秒/步 - 损失: 0.8777 - 稀疏分类准确率: 0.6545

1558/未知 707秒 453毫秒/步 - 损失: 0.8776 - 稀疏分类准确率: 0.6546

1559/未知 707秒 453毫秒/步 - 损失: 0.8774 - 稀疏分类准确率: 0.6546

1560/未知 708秒 453毫秒/步 - 损失: 0.8773 - 稀疏分类准确率: 0.6546

1561/未知 708秒 453毫秒/步 - 损失: 0.8772 - 稀疏分类准确率: 0.6547

1562/未知 708秒 453毫秒/步 - 损失: 0.8771 - 稀疏分类准确率: 0.6547

1563/未知 709秒 453毫秒/步 - 损失: 0.8770 - 稀疏分类准确率: 0.6547

1564/未知 709秒 453毫秒/步 - 损失: 0.8769 - 稀疏分类准确率: 0.6548

1565/未知 710秒 453毫秒/步 - 损失: 0.8768 - 稀疏分类准确率: 0.6548

1566/未知 710秒 453毫秒/步 - 损失: 0.8767 - 稀疏分类准确率: 0.6548

1567/未知 711秒 453毫秒/步 - 损失: 0.8766 - 稀疏分类准确率: 0.6549

1568/未知 711秒 453毫秒/步 - 损失: 0.8765 - 稀疏分类准确率: 0.6549

1569/未知 711秒 453毫秒/步 - 损失: 0.8763 - 稀疏分类准确率: 0.6549

1570/未知 712秒 453毫秒/步 - 损失: 0.8762 - 稀疏分类准确率: 0.6550

1571/未知 712秒 453毫秒/步 - 损失: 0.8761 - 稀疏分类准确率: 0.6550

1572/未知 713秒 453毫秒/步 - 损失: 0.8760 - 稀疏分类准确率: 0.6550

1573/未知 713秒 453毫秒/步 - 损失: 0.8759 - 稀疏分类准确率: 0.6551

1574/未知 714秒 453毫秒/步 - 损失: 0.8758 - 稀疏分类准确率: 0.6551

1575/未知 714秒 453毫秒/步 - 损失: 0.8757 - 稀疏分类准确率: 0.6552

1576/未知 715秒 453毫秒/步 - 损失: 0.8756 - 稀疏分类准确率: 0.6552

1577/未知 715秒 453毫秒/步 - 损失: 0.8755 - 稀疏分类准确率: 0.6552

1578/未知 715秒 453毫秒/步 - 损失: 0.8754 - 稀疏分类准确率: 0.6553

1579/未知 716秒 453毫秒/步 - 损失: 0.8753 - 稀疏分类准确率: 0.6553

1580/未知 716秒 453毫秒/步 - 损失: 0.8752 - 稀疏分类准确率: 0.6553

1581/未知 716秒 453毫秒/步 - 损失: 0.8750 - 稀疏分类准确率: 0.6554

1582/未知 717秒 453毫秒/步 - 损失: 0.8749 - 稀疏分类准确率: 0.6554

1583/未知 717秒 453毫秒/步 - 损失: 0.8748 - 稀疏分类准确率: 0.6554

1584/未知 718秒 453毫秒/步 - 损失: 0.8747 - 稀疏分类准确率: 0.6555

1585/未知 718秒 453毫秒/步 - 损失: 0.8746 - 稀疏分类准确率: 0.6555

1586/未知 718秒 453毫秒/步 - 损失: 0.8745 - 稀疏分类准确率: 0.6555

1587/未知 719秒 453毫秒/步 - 损失: 0.8744 - 稀疏分类准确率: 0.6556

1588/未知 719秒 453毫秒/步 - 损失: 0.8743 - 稀疏分类准确率: 0.6556

1589/未知 720秒 453毫秒/步 - 损失: 0.8742 - 稀疏分类准确率: 0.6556

1590/未知 720秒 453毫秒/步 - 损失: 0.8741 - 稀疏分类准确率: 0.6557

1591/未知 721秒 453毫秒/步 - 损失: 0.8740 - 稀疏分类准确率: 0.6557

1592/未知 721秒 452毫秒/步 - 损失: 0.8739 - 稀疏分类准确率: 0.6557

1593/未知 721秒 452毫秒/步 - 损失: 0.8738 - 稀疏分类准确率: 0.6558

1594/未知 722秒 452毫秒/步 - 损失: 0.8737 - 稀疏分类准确率: 0.6558

1595/未知 722秒 452毫秒/步 - 损失: 0.8735 - 稀疏分类准确率: 0.6558

1596/未知 723秒 452毫秒/步 - 损失: 0.8734 - 稀疏分类准确率: 0.6559

1597/未知 723秒 453毫秒/步 - 损失: 0.8733 - 稀疏分类准确率: 0.6559

1598/未知 724秒 453毫秒/步 - 损失: 0.8732 - 稀疏分类准确率: 0.6559

1599/未知 724秒 453毫秒/步 - 损失: 0.8731 - 稀疏分类准确率: 0.6560

1600/未知 725秒 453毫秒/步 - 损失: 0.8730 - 稀疏分类准确率: 0.6560

1601/未知 725秒 452毫秒/步 - 损失: 0.8729 - 稀疏分类准确率: 0.6560

1602/未知 725秒 452毫秒/步 - 损失: 0.8728 - 稀疏分类准确率: 0.6561

1603/未知 726秒 452毫秒/步 - 损失: 0.8727 - 稀疏分类准确率: 0.6561

1604/未知 726秒 452毫秒/步 - 损失: 0.8726 - 稀疏分类准确率: 0.6561

1605/未知 726秒 452毫秒/步 - 损失: 0.8725 - 稀疏分类准确率: 0.6562

1606/未知 727秒 452毫秒/步 - 损失: 0.8724 - 稀疏分类准确率: 0.6562

1607/未知 727秒 452毫秒/步 - 损失: 0.8723 - 稀疏分类准确率: 0.6562

1608/未知 728秒 452毫秒/步 - 损失: 0.8722 - 稀疏分类准确率: 0.6563

1609/未知 728秒 452毫秒/步 - 损失: 0.8721 - 稀疏分类准确率: 0.6563

1610/未知 728秒 452毫秒/步 - 损失: 0.8720 - 稀疏分类准确率: 0.6563

1611/未知 729秒 452毫秒/步 - 损失: 0.8719 - 稀疏分类准确率: 0.6564

1612/未知 729秒 452毫秒/步 - 损失: 0.8717 - 稀疏分类准确率: 0.6564

1613/未知 730秒 452毫秒/步 - 损失: 0.8716 - 稀疏分类准确率: 0.6564

1614/未知 730秒 452毫秒/步 - 损失: 0.8715 - 稀疏分类准确率: 0.6565

1615/未知 730秒 452毫秒/步 - 损失: 0.8714 - 稀疏分类准确率: 0.6565

1616/未知 731秒 452毫秒/步 - 损失: 0.8713 - 稀疏分类准确率: 0.6565

1617/未知 731秒 452毫秒/步 - 损失: 0.8712 - 稀疏分类准确率: 0.6566

1618/未知 732秒 452毫秒/步 - 损失: 0.8711 - 稀疏分类准确率: 0.6566

1619/未知 732秒 452毫秒/步 - 损失: 0.8710 - 稀疏分类准确率: 0.6566

1620/未知 733秒 452毫秒/步 - 损失: 0.8709 - 稀疏分类准确率: 0.6567

1621/未知 733秒 452毫秒/步 - 损失: 0.8708 - 稀疏分类准确率: 0.6567

1622/未知 734秒 452毫秒/步 - 损失: 0.8707 - 稀疏分类准确率: 0.6567

1623/未知 734秒 452毫秒/步 - 损失: 0.8706 - 稀疏分类准确率: 0.6567

1624/未知 734秒 452毫秒/步 - 损失: 0.8705 - 稀疏分类准确率: 0.6568

1625/未知 735秒 452毫秒/步 - 损失: 0.8704 - 稀疏分类准确率: 0.6568

1626/未知 735秒 452毫秒/步 - 损失: 0.8703 - 稀疏分类准确率: 0.6568

1627/未知 736秒 452毫秒/步 - 损失: 0.8702 - 稀疏分类准确率: 0.6569

1628/未知 736秒 452毫秒/步 - 损失: 0.8701 - 稀疏分类准确率: 0.6569

1629/未知 736秒 452毫秒/步 - 损失: 0.8700 - 稀疏分类准确率: 0.6569

1630/未知 737秒 452毫秒/步 - 损失: 0.8699 - 稀疏分类准确率: 0.6570

1631/未知 737秒 452毫秒/步 - 损失: 0.8698 - 稀疏分类准确率: 0.6570

1632/未知 738秒 452毫秒/步 - 损失: 0.8697 - 稀疏分类准确率: 0.6570

1633/未知 738秒 452毫秒/步 - 损失: 0.8696 - 稀疏分类准确率: 0.6571

1634/未知 738秒 451毫秒/步 - 损失: 0.8695 - 稀疏分类准确率: 0.6571

1635/未知 739秒 451毫秒/步 - 损失: 0.8694 - 稀疏分类准确率: 0.6571

1636/未知 739秒 451毫秒/步 - 损失: 0.8693 - 稀疏分类准确率: 0.6572

1637/未知 739秒 451毫秒/步 - 损失: 0.8692 - 稀疏分类准确率: 0.6572

1638/未知 740秒 451毫秒/步 - 损失: 0.8690 - 稀疏分类准确率: 0.6572

1639/未知 740秒 451毫秒/步 - 损失: 0.8689 - 稀疏分类准确率: 0.6573

1640/未知 741秒 451毫秒/步 - 损失: 0.8688 - 稀疏分类准确率: 0.6573

1641/未知 741秒 451毫秒/步 - 损失: 0.8687 - 稀疏分类准确率: 0.6573

1642/未知 742秒 451毫秒/步 - 损失: 0.8686 - 稀疏分类准确率: 0.6574

1643/未知 742秒 451毫秒/步 - 损失: 0.8685 - 稀疏分类准确率: 0.6574

1644/未知 743秒 451毫秒/步 - 损失: 0.8684 - 稀疏分类准确率: 0.6574

1645/未知 743秒 451毫秒/步 - 损失: 0.8683 - 稀疏分类准确率: 0.6575

1646/未知 743秒 451毫秒/步 - 损失: 0.8682 - 稀疏分类准确率: 0.6575

1647/未知 744秒 451毫秒/步 - 损失: 0.8681 - 稀疏分类准确率: 0.6575

1648/未知 744秒 451毫秒/步 - 损失: 0.8680 - 稀疏分类准确率: 0.6576

1649/未知 744秒 451毫秒/步 - 损失: 0.8679 - 稀疏分类准确率: 0.6576

1650/未知 745秒 451毫秒/步 - 损失: 0.8678 - 稀疏分类准确率: 0.6576

1651/未知 745秒 451毫秒/步 - 损失: 0.8677 - 稀疏分类准确率: 0.6577

1652/未知 746秒 451毫秒/步 - 损失: 0.8676 - 稀疏分类准确率: 0.6577

1653/未知 746秒 451毫秒/步 - 损失: 0.8675 - 稀疏分类准确率: 0.6577

1654/未知 746秒 451毫秒/步 - 损失: 0.8674 - 稀疏分类准确率: 0.6577

1655/未知 747秒 451毫秒/步 - 损失: 0.8673 - 稀疏分类准确率: 0.6578

1656/未知 747秒 451毫秒/步 - 损失: 0.8672 - 稀疏分类准确率: 0.6578

1657/未知 748秒 451毫秒/步 - 损失: 0.8671 - 稀疏分类准确率: 0.6578

1658/未知 748秒 451毫秒/步 - 损失: 0.8670 - 稀疏分类准确率: 0.6579

1659/未知 749秒 451毫秒/步 - 损失: 0.8669 - 稀疏分类准确率: 0.6579

1660/未知 749秒 451毫秒/步 - 损失: 0.8668 - 稀疏分类准确率: 0.6579

1661/未知 749秒 451毫秒/步 - 损失: 0.8667 - 稀疏分类准确率: 0.6580

1662/未知 750秒 451毫秒/步 - 损失: 0.8666 - 稀疏分类准确率: 0.6580

1663/未知 750秒 451毫秒/步 - 损失: 0.8665 - 稀疏分类准确率: 0.6580

1664/未知 750秒 451毫秒/步 - 损失: 0.8664 - 稀疏分类准确率: 0.6581

1665/未知 751秒 451毫秒/步 - 损失: 0.8663 - 稀疏分类准确率: 0.6581

1666/未知 751秒 451毫秒/步 - 损失: 0.8662 - 稀疏分类准确率: 0.6581

1667/未知 752秒 451毫秒/步 - 损失: 0.8661 - 稀疏分类准确率: 0.6582

1668/未知 752秒 451毫秒/步 - 损失: 0.8660 - 稀疏分类准确率: 0.6582

1669/未知 753秒 451毫秒/步 - 损失: 0.8659 - 稀疏分类准确率: 0.6582

1670/未知 753秒 451毫秒/步 - 损失: 0.8658 - 稀疏分类准确率: 0.6583

1671/未知 754秒 451毫秒/步 - 损失: 0.8657 - 稀疏分类准确率: 0.6583

1672/未知 754秒 451毫秒/步 - 损失: 0.8656 - 稀疏分类准确率: 0.6583

1673/未知 755秒 451毫秒/步 - 损失: 0.8655 - 稀疏分类准确率: 0.6583

1674/未知 755秒 451毫秒/步 - 损失: 0.8654 - 稀疏分类准确率: 0.6584

1675/未知 755秒 451毫秒/步 - 损失: 0.8653 - 稀疏分类准确率: 0.6584

1676/未知 756秒 451毫秒/步 - 损失: 0.8652 - 稀疏分类准确率: 0.6584

1677/未知 756秒 451毫秒/步 - 损失: 0.8651 - 稀疏分类准确率: 0.6585

1678/未知 757秒 451毫秒/步 - 损失: 0.8650 - 稀疏分类准确率: 0.6585

1679/未知 757秒 450毫秒/步 - 损失: 0.8649 - 稀疏分类准确率: 0.6585

1680/未知 757秒 450毫秒/步 - 损失: 0.8648 - 稀疏分类准确率: 0.6586

1681/未知 758秒 450毫秒/步 - 损失: 0.8647 - 稀疏分类准确率: 0.6586

1682/未知 758秒 450毫秒/步 - 损失: 0.8646 - 稀疏分类准确率: 0.6586

1683/未知 758秒 450毫秒/步 - 损失: 0.8645 - 稀疏分类准确率: 0.6587

1684/未知 759秒 450毫秒/步 - 损失: 0.8644 - 稀疏分类准确率: 0.6587

1685/未知 759秒 450毫秒/步 - 损失: 0.8643 - 稀疏分类准确率: 0.6587

1686/未知 760秒 450毫秒/步 - 损失: 0.8642 - 稀疏分类准确率: 0.6587

1687/未知 760秒 450毫秒/步 - 损失: 0.8641 - 稀疏分类准确率: 0.6588

1688/未知 760秒 450毫秒/步 - 损失: 0.8640 - 稀疏分类准确率: 0.6588

1689/未知 761秒 450毫秒/步 - 损失: 0.8639 - 稀疏分类准确率: 0.6588

1690/未知 761秒 450毫秒/步 - 损失: 0.8638 - 稀疏分类准确率: 0.6589

1691/未知 762秒 450毫秒/步 - 损失: 0.8637 - 稀疏分类准确率: 0.6589

1692/未知 762秒 450毫秒/步 - 损失: 0.8636 - 稀疏分类准确率: 0.6589

1693/未知 762秒 450毫秒/步 - 损失: 0.8635 - 稀疏分类准确率: 0.6590

1694/未知 763秒 450毫秒/步 - 损失: 0.8634 - 稀疏分类准确率: 0.6590

1695/未知 763秒 450毫秒/步 - 损失: 0.8633 - 稀疏分类准确率: 0.6590

1696/未知 764秒 450毫秒/步 - 损失: 0.8632 - 稀疏分类准确率: 0.6591

1697/未知 764秒 450毫秒/步 - 损失: 0.8632 - 稀疏分类准确率: 0.6591

1698/未知 765秒 450毫秒/步 - 损失: 0.8631 - 稀疏分类准确率: 0.6591

1699/未知 765秒 450毫秒/步 - 损失: 0.8630 - 稀疏分类准确率: 0.6591

1700/未知 766秒 450毫秒/步 - 损失: 0.8629 - 稀疏分类准确率: 0.6592

1701/未知 766秒 450毫秒/步 - 损失: 0.8628 - 稀疏分类准确率: 0.6592

1702/未知 766秒 450毫秒/步 - 损失: 0.8627 - 稀疏分类准确率: 0.6592

1703/未知 767秒 450毫秒/步 - 损失: 0.8626 - 稀疏分类准确率: 0.6593

1704/未知 767秒 450毫秒/步 - 损失: 0.8625 - 稀疏分类准确率: 0.6593

1705/未知 768秒 450毫秒/步 - 损失: 0.8624 - 稀疏分类准确率: 0.6593

1706/未知 768秒 450毫秒/步 - 损失: 0.8623 - 稀疏分类准确率: 0.6594

1707/未知 768秒 450毫秒/步 - 损失: 0.8622 - 稀疏分类准确率: 0.6594

1708/未知 769秒 450毫秒/步 - 损失: 0.8621 - 稀疏分类准确率: 0.6594

1709/未知 769秒 450毫秒/步 - 损失: 0.8620 - 稀疏分类准确率: 0.6595

1710/未知 770秒 450毫秒/步 - 损失: 0.8619 - 稀疏分类准确率: 0.6595

1711/未知 770秒 450毫秒/步 - 损失: 0.8618 - 稀疏分类准确率: 0.6595

1712/未知 770秒 450毫秒/步 - 损失: 0.8617 - 稀疏分类准确率: 0.6595

1713/未知 771秒 450毫秒/步 - 损失: 0.8616 - 稀疏分类准确率: 0.6596

1714/未知 771秒 450毫秒/步 - 损失: 0.8615 - 稀疏分类准确率: 0.6596

1715/未知 772秒 450毫秒/步 - 损失: 0.8614 - 稀疏分类准确率: 0.6596

1716/未知 772秒 450毫秒/步 - 损失: 0.8613 - 稀疏分类准确率: 0.6597

1717/未知 773秒 450毫秒/步 - 损失: 0.8612 - 稀疏分类准确率: 0.6597

1718/未知 773秒 450毫秒/步 - 损失: 0.8611 - 稀疏分类准确率: 0.6597

1719/未知 774秒 450毫秒/步 - 损失: 0.8610 - 稀疏分类准确率: 0.6598

1720/未知 774秒 450毫秒/步 - 损失: 0.8609 - 稀疏分类准确率: 0.6598

1721/未知 774秒 450毫秒/步 - 损失: 0.8608 - 稀疏分类准确率: 0.6598

1722/未知 775秒 450毫秒/步 - 损失: 0.8607 - 稀疏分类准确率: 0.6598

1723/未知 775秒 450毫秒/步 - 损失: 0.8606 - 稀疏分类准确率: 0.6599

1724/未知 776秒 450毫秒/步 - 损失: 0.8606 - 稀疏分类准确率: 0.6599

1725/未知 776秒 450毫秒/步 - 损失: 0.8605 - 稀疏分类准确率: 0.6599

1726/未知 777秒 450毫秒/步 - 损失: 0.8604 - 稀疏分类准确率: 0.6600

1727/未知 777秒 450毫秒/步 - 损失: 0.8603 - 稀疏分类准确率: 0.6600

1728/未知 777秒 450毫秒/步 - 损失: 0.8602 - 稀疏分类准确率: 0.6600

1729/未知 778秒 450毫秒/步 - 损失: 0.8601 - 稀疏分类准确率: 0.6601

1730/未知 778秒 449毫秒/步 - 损失: 0.8600 - 稀疏分类准确率: 0.6601

1731/未知 779秒 449毫秒/步 - 损失: 0.8599 - 稀疏分类准确率: 0.6601

1732/未知 779秒 449毫秒/步 - 损失: 0.8598 - 稀疏分类准确率: 0.6601

1733/未知 779秒 449毫秒/步 - 损失: 0.8597 - 稀疏分类准确率: 0.6602

1734/未知 780秒 449毫秒/步 - 损失: 0.8596 - 稀疏分类准确率: 0.6602

1735/未知 780秒 449毫秒/步 - 损失: 0.8595 - 稀疏分类准确率: 0.6602

1736/未知 780秒 449毫秒/步 - 损失: 0.8594 - 稀疏分类准确率: 0.6603

1737/未知 781秒 449毫秒/步 - 损失: 0.8593 - 稀疏分类准确率: 0.6603

1738/未知 781秒 449毫秒/步 - 损失: 0.8592 - 稀疏分类准确率: 0.6603

1739/未知 782秒 449毫秒/步 - 损失: 0.8591 - 稀疏分类准确率: 0.6603

1740/未知 782秒 449毫秒/步 - 损失: 0.8590 - 稀疏分类准确率: 0.6604

1741/未知 782秒 449毫秒/步 - 损失: 0.8589 - 稀疏分类准确率: 0.6604

1742/未知 783秒 449毫秒/步 - 损失: 0.8589 - 稀疏分类准确率: 0.6604

1743/未知 783秒 449毫秒/步 - 损失: 0.8588 - 稀疏分类准确率: 0.6605

1744/未知 784秒 449毫秒/步 - 损失: 0.8587 - 稀疏分类准确率: 0.6605

1745/未知 784秒 449毫秒/步 - 损失: 0.8586 - 稀疏分类准确率: 0.6605

1746/未知 785秒 449毫秒/步 - 损失: 0.8585 - 稀疏分类准确率: 0.6606

1747/未知 785秒 449毫秒/步 - 损失: 0.8584 - 稀疏分类准确率: 0.6606

1748/未知 786秒 449毫秒/步 - 损失: 0.8583 - 稀疏分类准确率: 0.6606

1749/未知 786秒 449毫秒/步 - 损失: 0.8582 - 稀疏分类准确率: 0.6606

1750/未知 787秒 449毫秒/步 - 损失: 0.8581 - 稀疏分类准确率: 0.6607

1751/未知 787秒 449毫秒/步 - 损失: 0.8580 - 稀疏分类准确率: 0.6607

1752/未知 787秒 449毫秒/步 - 损失: 0.8579 - 稀疏分类准确率: 0.6607

1753/未知 788秒 449毫秒/步 - 损失: 0.8578 - 稀疏分类准确率: 0.6608

1754/未知 788秒 449毫秒/步 - 损失: 0.8577 - 稀疏分类准确率: 0.6608

1755/未知 789秒 449毫秒/步 - 损失: 0.8576 - 稀疏分类准确率: 0.6608

1756/未知 789秒 449毫秒/步 - 损失: 0.8576 - 稀疏分类准确率: 0.6608

1757/未知 789秒 449毫秒/步 - 损失: 0.8575 - 稀疏分类准确率: 0.6609

1758/未知 790秒 449毫秒/步 - 损失: 0.8574 - 稀疏分类准确率: 0.6609

1759/未知 790秒 449毫秒/步 - 损失: 0.8573 - 稀疏分类准确率: 0.6609

1760/未知 791秒 449毫秒/步 - 损失: 0.8572 - 稀疏分类准确率: 0.6610

1761/未知 791秒 449毫秒/步 - 损失: 0.8571 - 稀疏分类准确率: 0.6610

1762/未知 792秒 449毫秒/步 - 损失: 0.8570 - 稀疏分类准确率: 0.6610

1763/未知 792秒 449毫秒/步 - 损失: 0.8569 - 稀疏分类准确率: 0.6610

1764/未知 792秒 449毫秒/步 - 损失: 0.8568 - 稀疏分类准确率: 0.6611

1765/未知 793秒 449毫秒/步 - 损失: 0.8567 - 稀疏分类准确率: 0.6611

1766/未知 793秒 449毫秒/步 - 损失: 0.8566 - 稀疏分类准确率: 0.6611

1767/未知 794秒 449毫秒/步 - 损失: 0.8565 - 稀疏分类准确率: 0.6612

1768/未知 794秒 449毫秒/步 - 损失: 0.8564 - 稀疏分类准确率: 0.6612

1769/未知 795秒 449毫秒/步 - 损失: 0.8564 - 稀疏分类准确率: 0.6612

1770/未知 795秒 449毫秒/步 - 损失: 0.8563 - 稀疏分类准确率: 0.6612

1771/未知 796秒 449毫秒/步 - 损失: 0.8562 - 稀疏分类准确率: 0.6613

1772/未知 796秒 449毫秒/步 - 损失: 0.8561 - 稀疏分类准确率: 0.6613

1773/未知 796秒 449毫秒/步 - 损失: 0.8560 - 稀疏分类准确率: 0.6613

1774/未知 797秒 449毫秒/步 - 损失: 0.8559 - 稀疏分类准确率: 0.6614

1775/未知 797秒 449毫秒/步 - 损失: 0.8558 - 稀疏分类准确率: 0.6614

1776/未知 797秒 449毫秒/步 - 损失: 0.8557 - 稀疏分类准确率: 0.6614

1777/未知 798秒 449毫秒/步 - 损失: 0.8556 - 稀疏分类准确率: 0.6614

1778/未知 798秒 449毫秒/步 - 损失: 0.8555 - 稀疏分类准确率: 0.6615

1779/未知 799秒 449毫秒/步 - 损失: 0.8554 - 稀疏分类准确率: 0.6615

1780/未知 799秒 449毫秒/步 - 损失: 0.8554 - 稀疏分类准确率: 0.6615

1781/未知 799秒 449毫秒/步 - 损失: 0.8553 - 稀疏分类准确率: 0.6616

1782/未知 800秒 449毫秒/步 - 损失: 0.8552 - 稀疏分类准确率: 0.6616

1783/未知 800秒 448毫秒/步 - 损失: 0.8551 - 稀疏分类准确率: 0.6616

1784/未知 801秒 448毫秒/步 - 损失: 0.8550 - 稀疏分类准确率: 0.6616

1785/未知 801秒 448毫秒/步 - 损失: 0.8549 - 稀疏分类准确率: 0.6617

1786/未知 801秒 448毫秒/步 - 损失: 0.8548 - 稀疏分类准确率: 0.6617

1787/未知 802秒 448毫秒/步 - 损失: 0.8547 - 稀疏分类准确率: 0.6617

1788/未知 802秒 448毫秒/步 - 损失: 0.8546 - 稀疏分类准确率: 0.6618

1789/未知 803秒 448毫秒/步 - 损失: 0.8545 - 稀疏分类准确率: 0.6618

1790/未知 803秒 448毫秒/步 - 损失: 0.8545 - 稀疏分类准确率: 0.6618

1791/未知 803秒 448毫秒/步 - 损失: 0.8544 - 稀疏分类准确率: 0.6618

1792/未知 804秒 448毫秒/步 - 损失: 0.8543 - 稀疏分类准确率: 0.6619

1793/未知 804秒 448毫秒/步 - 损失: 0.8542 - 稀疏分类准确率: 0.6619

1794/未知 805秒 448毫秒/步 - 损失: 0.8541 - 稀疏分类准确率: 0.6619

1795/未知 805秒 448毫秒/步 - 损失: 0.8540 - 稀疏分类准确率: 0.6620

1796/未知 805秒 448毫秒/步 - 损失: 0.8539 - 稀疏分类准确率: 0.6620

1797/未知 806秒 448毫秒/步 - 损失: 0.8538 - 稀疏分类准确率: 0.6620

1798/未知 806秒 448毫秒/步 - 损失: 0.8537 - 稀疏分类准确率: 0.6620

1799/未知 807秒 448毫秒/步 - 损失: 0.8536 - 稀疏分类准确率: 0.6621

1800/未知 807秒 448毫秒/步 - 损失: 0.8536 - 稀疏分类准确率: 0.6621

1801/未知 808秒 448毫秒/步 - 损失: 0.8535 - 稀疏分类准确率: 0.6621

1802/未知 808秒 448毫秒/步 - 损失: 0.8534 - 稀疏分类准确率: 0.6622

1803/未知 808秒 448毫秒/步 - 损失: 0.8533 - 稀疏分类准确率: 0.6622

1804/未知 809秒 448毫秒/步 - 损失: 0.8532 - 稀疏分类准确率: 0.6622

1805/未知 809秒 448毫秒/步 - 损失: 0.8531 - 稀疏分类准确率: 0.6622

1806/未知 810秒 448毫秒/步 - 损失: 0.8530 - 稀疏分类准确率: 0.6623

1807/未知 810秒 448毫秒/步 - 损失: 0.8529 - 稀疏分类准确率: 0.6623

1808/未知 811秒 448毫秒/步 - 损失: 0.8528 - 稀疏分类准确率: 0.6623

1809/未知 811秒 448毫秒/步 - 损失: 0.8528 - 稀疏分类准确率: 0.6623

1810/未知 811秒 448毫秒/步 - 损失: 0.8527 - 稀疏分类准确率: 0.6624

1811/未知 812秒 448毫秒/步 - 损失: 0.8526 - 稀疏分类准确率: 0.6624

1812/未知 812秒 448毫秒/步 - 损失: 0.8525 - 稀疏分类准确率: 0.6624

1813/未知 812秒 448毫秒/步 - 损失: 0.8524 - 稀疏分类准确率: 0.6625

1814/未知 813秒 448毫秒/步 - 损失: 0.8523 - 稀疏分类准确率: 0.6625

1815/未知 813秒 448毫秒/步 - 损失: 0.8522 - 稀疏分类准确率: 0.6625

1816/未知 814秒 448毫秒/步 - 损失: 0.8521 - 稀疏分类准确率: 0.6625

1817/未知 814秒 448毫秒/步 - 损失: 0.8520 - 稀疏分类准确率: 0.6626

1818/未知 814秒 448毫秒/步 - 损失: 0.8520 - 稀疏分类准确率: 0.6626

1819/未知 815秒 448毫秒/步 - 损失: 0.8519 - 稀疏分类准确率: 0.6626

1820/未知 815秒 448毫秒/步 - 损失: 0.8518 - 稀疏分类准确率: 0.6627

1821/未知 816秒 448毫秒/步 - 损失: 0.8517 - 稀疏分类准确率: 0.6627

1822/未知 816秒 448毫秒/步 - 损失: 0.8516 - 稀疏分类准确率: 0.6627

1823/未知 817秒 448毫秒/步 - 损失: 0.8515 - 稀疏分类准确率: 0.6627

1824/未知 817秒 448毫秒/步 - 损失: 0.8514 - 稀疏分类准确率: 0.6628

1825/未知 818秒 448毫秒/步 - 损失: 0.8513 - 稀疏分类准确率: 0.6628

1826/未知 818秒 448毫秒/步 - 损失: 0.8513 - 稀疏分类准确率: 0.6628

1827/未知 819秒 448毫秒/步 - 损失: 0.8512 - 稀疏分类准确率: 0.6628

1828/未知 819秒 448毫秒/步 - 损失: 0.8511 - 稀疏分类准确率: 0.6629

1829/未知 819秒 448毫秒/步 - 损失: 0.8510 - 稀疏分类准确率: 0.6629

1830/未知 820秒 448毫秒/步 - 损失: 0.8509 - 稀疏分类准确率: 0.6629

1831/未知 820秒 448毫秒/步 - 损失: 0.8508 - 稀疏分类准确率: 0.6630

1832/未知 821秒 448毫秒/步 - 损失: 0.8507 - 稀疏分类准确率: 0.6630

1833/未知 821秒 448毫秒/步 - 损失: 0.8507 - 稀疏分类准确率: 0.6630

1834/未知 821秒 448毫秒/步 - 损失: 0.8506 - 稀疏分类准确率: 0.6630

1835/未知 822秒 447毫秒/步 - 损失: 0.8505 - 稀疏分类准确率: 0.6631

1836/未知 822秒 447毫秒/步 - 损失: 0.8504 - 稀疏分类准确率: 0.6631

1837/未知 822秒 447毫秒/步 - 损失: 0.8503 - 稀疏分类准确率: 0.6631

1838/未知 823秒 447毫秒/步 - 损失: 0.8502 - 稀疏分类准确率: 0.6631

1839/未知 823秒 447毫秒/步 - 损失: 0.8501 - 稀疏分类准确率: 0.6632

1840/未知 823秒 447毫秒/步 - 损失: 0.8500 - 稀疏分类准确率: 0.6632

1841/未知 824秒 447毫秒/步 - 损失: 0.8500 - 稀疏分类准确率: 0.6632

1842/未知 824秒 447毫秒/步 - 损失: 0.8499 - 稀疏分类准确率: 0.6633

1843/未知 825秒 447毫秒/步 - 损失: 0.8498 - 稀疏分类准确率: 0.6633

1844/未知 825秒 447毫秒/步 - 损失: 0.8497 - 稀疏分类准确率: 0.6633

1845/未知 825秒 447毫秒/步 - 损失: 0.8496 - 稀疏分类准确率: 0.6633

1846/未知 826秒 447毫秒/步 - 损失: 0.8495 - 稀疏分类准确率: 0.6634

1847/未知 826秒 447毫秒/步 - 损失: 0.8494 - 稀疏分类准确率: 0.6634

1848/未知 827秒 447毫秒/步 - 损失: 0.8494 - 稀疏分类准确率: 0.6634

1849/未知 827秒 447毫秒/步 - 损失: 0.8493 - 稀疏分类准确率: 0.6634

1850/未知 828秒 447毫秒/步 - 损失: 0.8492 - 稀疏分类准确率: 0.6635

1851/未知 828秒 447毫秒/步 - 损失: 0.8491 - 稀疏分类准确率: 0.6635

1852/未知 828秒 447毫秒/步 - 损失: 0.8490 - 稀疏分类准确率: 0.6635

1853/未知 829秒 447毫秒/步 - 损失: 0.8489 - 稀疏分类准确率: 0.6636

1854/未知 829秒 447毫秒/步 - 损失: 0.8488 - 稀疏分类准确率: 0.6636

1855/未知 830秒 447毫秒/步 - 损失: 0.8488 - 稀疏分类准确率: 0.6636

1856/未知 830秒 447毫秒/步 - 损失: 0.8487 - 稀疏分类准确率: 0.6636

1857/未知 830秒 447毫秒/步 - 损失: 0.8486 - 稀疏分类准确率: 0.6637

1858/未知 831秒 447毫秒/步 - 损失: 0.8485 - 稀疏分类准确率: 0.6637

1859/未知 831秒 447毫秒/步 - 损失: 0.8484 - 稀疏分类准确率: 0.6637

1860/未知 832秒 447毫秒/步 - 损失: 0.8483 - 稀疏分类准确率: 0.6637

1861/未知 832秒 447毫秒/步 - 损失: 0.8482 - 稀疏分类准确率: 0.6638

1862/未知 832秒 448毫秒/步 - 损失: 0.8482 - 稀疏分类准确率: 0.6638

1863/未知 833秒 447毫秒/步 - 损失: 0.8481 - 稀疏分类准确率: 0.6638

1864/未知 833秒 447毫秒/步 - 损失: 0.8480 - 稀疏分类准确率: 0.6638

1865/未知 834秒 447毫秒/步 - 损失: 0.8479 - 稀疏分类准确率: 0.6639

1865/1865 ━━━━━━━━━━━━━━━━━━━━ 834秒 447毫秒/步 - 损失: 0.8478 - 稀疏分类准确率: 0.6639

Model training finished

/home/humbulani/tensorflow-env/env/lib/python3.11/site-packages/keras/src/trainers/epoch_iterator.py:151: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
  self._interrupted_warning()

Test accuracy: 75.0%

深度交叉模型在测试集上达到了约 81% 的准确率。

结论

您可以使用 Keras 预处理层轻松处理具有不同编码机制的类别特征，包括独热编码和特征嵌入。此外，不同的模型架构——如宽、深度和交叉网络——对于不同的数据集特性具有不同的优势。您可以探索独立使用它们或将它们组合起来，以获得最适合您数据集的结果。