IMDB 上的双向 LSTM
作者： fchollet
创建日期 2020/05/03
最后修改日期 2020/05/03
描述：在 IMDB 电影评论情感分类数据集上训练一个两层双向 LSTM。
设置
import numpy as np
import keras
from keras import layers
max_features = 20000 # Only consider the top 20k words
maxlen = 200 # Only consider the first 200 words of each movie review
构建模型
# Input for variable-length sequences of integers
inputs = keras.Input(shape=(None,), dtype="int32")
# Embed each integer in a 128-dimensional vector
x = layers.Embedding(max_features, 128)(inputs)
# Add 2 bidirectional LSTMs
x = layers.Bidirectional(layers.LSTM(64, return_sequences=True))(x)
x = layers.Bidirectional(layers.LSTM(64))(x)
# Add a classifier
outputs = layers.Dense(1, activation="sigmoid")(x)
model = keras.Model(inputs, outputs)
model.summary()
Model: "functional_1"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓ ┃ Layer (type) ┃ Output Shape ┃ Param # ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩ │ input_layer (InputLayer) │ (None, None) │ 0 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ embedding (Embedding) │ (None, None, 128) │ 2,560,000 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ bidirectional (Bidirectional) │ (None, None, 128) │ 98,816 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ bidirectional_1 (Bidirectional) │ (None, 128) │ 98,816 │ ├─────────────────────────────────┼───────────────────────────┼────────────┤ │ dense (Dense) │ (None, 1) │ 129 │ └─────────────────────────────────┴───────────────────────────┴────────────┘
Total params: 2,757,761 (10.52 MB)
Trainable params: 2,757,761 (10.52 MB)
Non-trainable params: 0 (0.00 B)
加载 IMDB 电影评论情感数据
(x_train, y_train), (x_val, y_val) = keras.datasets.imdb.load_data(
num_words=max_features
)
print(len(x_train), "Training sequences")
print(len(x_val), "Validation sequences")
# Use pad_sequence to standardize sequence length:
# this will truncate sequences longer than 200 words and zero-pad sequences shorter than 200 words.
x_train = keras.utils.pad_sequences(x_train, maxlen=maxlen)
x_val = keras.utils.pad_sequences(x_val, maxlen=maxlen)
Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
17464789/17464789 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step
25000 Training sequences
25000 Validation sequences
训练和评估模型
您可以使用托管在 Hugging Face Hub 上的训练模型，并在 Hugging Face Spaces 上尝试演示。
model.compile(optimizer="adam", loss="binary_crossentropy", metrics=["accuracy"])
model.fit(x_train, y_train, batch_size=32, epochs=2, validation_data=(x_val, y_val))
Epoch 1/2
782/782 ━━━━━━━━━━━━━━━━━━━━ 61s 75ms/step - accuracy: 0.7540 - loss: 0.4697 - val_accuracy: 0.8269 - val_loss: 0.4202
Epoch 2/2
782/782 ━━━━━━━━━━━━━━━━━━━━ 54s 69ms/step - accuracy: 0.9151 - loss: 0.2263 - val_accuracy: 0.8428 - val_loss: 0.3650
<keras.src.callbacks.history.History at 0x7f3efd663850>