作者: Sayak Paul
创建日期 2021/06/19
上次修改日期 2021/06/19
描述:使用 AdaMatch 统一半监督学习和无监督域适应。
在本示例中,我们将实现 AdaMatch 算法,该算法由 Berthelot 等人在 AdaMatch:半监督学习和域适应的统一方法 中提出。它在无监督域适应方面取得了新的最先进水平(截至 2021 年 6 月)。AdaMatch 尤其令人感兴趣,因为它在一个框架下统一了半监督学习 (SSL) 和无监督域适应 (UDA)。因此,它提供了一种执行半监督域适应 (SSDA) 的方法。
此示例需要 TensorFlow 2.5 或更高版本,以及 TensorFlow Models,可以使用以下命令安装
!pip install -q tf-models-official==2.9.2
在继续之前,让我们回顾一下此示例基础上的几个初步概念。
在**半监督学习 (SSL)** 中,我们使用少量标记数据来训练模型,这些模型用于更大的未标记数据集。计算机视觉中流行的半监督学习方法包括 FixMatch、MixMatch、Noisy Student Training 等。您可以参考 此示例 以了解标准 SSL 工作流程的外观。
在**无监督域适应**中,我们可以访问源标记数据集和目标未标记数据集。然后,任务是学习一个可以很好地泛化到目标数据集的模型。源数据集和目标数据集在分布方面存在差异。下图对此想法进行了说明。在本示例中,我们使用 MNIST 数据集 作为源数据集,而目标数据集是 SVHN,它包含房屋编号的图像。这两个数据集在纹理、视角、外观等方面存在各种不同的因素:它们的域或分布彼此不同。
深度学习中流行的域适应算法包括 Deep CORAL、矩匹配 等。
import tensorflow as tf
tf.random.set_seed(42)
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import regularizers
from keras_cv.layers import RandAugment
import tensorflow_datasets as tfds
tfds.disable_progress_bar()
# MNIST
(
(mnist_x_train, mnist_y_train),
(mnist_x_test, mnist_y_test),
) = keras.datasets.mnist.load_data()
# Add a channel dimension
mnist_x_train = tf.expand_dims(mnist_x_train, -1)
mnist_x_test = tf.expand_dims(mnist_x_test, -1)
# Convert the labels to one-hot encoded vectors
mnist_y_train = tf.one_hot(mnist_y_train, 10).numpy()
# SVHN
svhn_train, svhn_test = tfds.load(
"svhn_cropped", split=["train", "test"], as_supervised=True
)
RESIZE_TO = 32
SOURCE_BATCH_SIZE = 64
TARGET_BATCH_SIZE = 3 * SOURCE_BATCH_SIZE # Reference: Section 3.2
EPOCHS = 10
STEPS_PER_EPOCH = len(mnist_x_train) // SOURCE_BATCH_SIZE
TOTAL_STEPS = EPOCHS * STEPS_PER_EPOCH
AUTO = tf.data.AUTOTUNE
LEARNING_RATE = 0.03
WEIGHT_DECAY = 0.0005
INIT = "he_normal"
DEPTH = 28
WIDTH_MULT = 2
SSL 算法的一个标准元素是将同一图像的弱增强版本和强增强版本馈送到学习模型,以使其预测保持一致。对于强增强,RandAugment 是一个标准选择。对于弱增强,我们将使用水平翻转和随机裁剪。
# Initialize `RandAugment` object with 2 layers of
# augmentation transforms and strength of 5.
augmenter = RandAugment(value_range=(0, 255), augmentations_per_image=2, magnitude=0.5)
def weak_augment(image, source=True):
if image.dtype != tf.float32:
image = tf.cast(image, tf.float32)
# MNIST images are grayscale, this is why we first convert them to
# RGB images.
if source:
image = tf.image.resize_with_pad(image, RESIZE_TO, RESIZE_TO)
image = tf.tile(image, [1, 1, 3])
image = tf.image.random_flip_left_right(image)
image = tf.image.random_crop(image, (RESIZE_TO, RESIZE_TO, 3))
return image
def strong_augment(image, source=True):
if image.dtype != tf.float32:
image = tf.cast(image, tf.float32)
if source:
image = tf.image.resize_with_pad(image, RESIZE_TO, RESIZE_TO)
image = tf.tile(image, [1, 1, 3])
image = augmenter(image)
return image
def create_individual_ds(ds, aug_func, source=True):
if source:
batch_size = SOURCE_BATCH_SIZE
else:
# During training 3x more target unlabeled samples are shown
# to the model in AdaMatch (Section 3.2 of the paper).
batch_size = TARGET_BATCH_SIZE
ds = ds.shuffle(batch_size * 10, seed=42)
if source:
ds = ds.map(lambda x, y: (aug_func(x), y), num_parallel_calls=AUTO)
else:
ds = ds.map(lambda x, y: (aug_func(x, False), y), num_parallel_calls=AUTO)
ds = ds.batch(batch_size).prefetch(AUTO)
return ds
_w
和 _s
后缀分别表示弱增强和强增强。
source_ds = tf.data.Dataset.from_tensor_slices((mnist_x_train, mnist_y_train))
source_ds_w = create_individual_ds(source_ds, weak_augment)
source_ds_s = create_individual_ds(source_ds, strong_augment)
final_source_ds = tf.data.Dataset.zip((source_ds_w, source_ds_s))
target_ds_w = create_individual_ds(svhn_train, weak_augment, source=False)
target_ds_s = create_individual_ds(svhn_train, strong_augment, source=False)
final_target_ds = tf.data.Dataset.zip((target_ds_w, target_ds_s))
下面是一个图像批次的示例
def compute_loss_source(source_labels, logits_source_w, logits_source_s):
loss_func = keras.losses.CategoricalCrossentropy(from_logits=True)
# First compute the losses between original source labels and
# predictions made on the weakly and strongly augmented versions
# of the same images.
w_loss = loss_func(source_labels, logits_source_w)
s_loss = loss_func(source_labels, logits_source_s)
return w_loss + s_loss
def compute_loss_target(target_pseudo_labels_w, logits_target_s, mask):
loss_func = keras.losses.CategoricalCrossentropy(from_logits=True, reduction="none")
target_pseudo_labels_w = tf.stop_gradient(target_pseudo_labels_w)
# For calculating loss for the target samples, we treat the pseudo labels
# as the ground-truth. These are not considered during backpropagation
# which is a standard SSL practice.
target_loss = loss_func(target_pseudo_labels_w, logits_target_s)
# More on `mask` later.
mask = tf.cast(mask, target_loss.dtype)
target_loss *= mask
return tf.reduce_mean(target_loss, 0)
下图展示了 AdaMatch 的整体工作流程(摘自原始论文)
以下是工作流程的简要分步说明
class AdaMatch(keras.Model):
def __init__(self, model, total_steps, tau=0.9):
super().__init__()
self.model = model
self.tau = tau # Denotes the confidence threshold
self.loss_tracker = tf.keras.metrics.Mean(name="loss")
self.total_steps = total_steps
self.current_step = tf.Variable(0, dtype="int64")
@property
def metrics(self):
return [self.loss_tracker]
# This is a warmup schedule to update the weight of the
# loss contributed by the target unlabeled samples. More
# on this in the text.
def compute_mu(self):
pi = tf.constant(np.pi, dtype="float32")
step = tf.cast(self.current_step, dtype="float32")
return 0.5 - tf.cos(tf.math.minimum(pi, (2 * pi * step) / self.total_steps)) / 2
def train_step(self, data):
## Unpack and organize the data ##
source_ds, target_ds = data
(source_w, source_labels), (source_s, _) = source_ds
(
(target_w, _),
(target_s, _),
) = target_ds # Notice that we are NOT using any labels here.
combined_images = tf.concat([source_w, source_s, target_w, target_s], 0)
combined_source = tf.concat([source_w, source_s], 0)
total_source = tf.shape(combined_source)[0]
total_target = tf.shape(tf.concat([target_w, target_s], 0))[0]
with tf.GradientTape() as tape:
## Forward passes ##
combined_logits = self.model(combined_images, training=True)
z_d_prime_source = self.model(
combined_source, training=False
) # No BatchNorm update.
z_prime_source = combined_logits[:total_source]
## 1. Random logit interpolation for the source images ##
lambd = tf.random.uniform((total_source, 10), 0, 1)
final_source_logits = (lambd * z_prime_source) + (
(1 - lambd) * z_d_prime_source
)
## 2. Distribution alignment (only consider weakly augmented images) ##
# Compute softmax for logits of the WEAKLY augmented SOURCE images.
y_hat_source_w = tf.nn.softmax(final_source_logits[: tf.shape(source_w)[0]])
# Extract logits for the WEAKLY augmented TARGET images and compute softmax.
logits_target = combined_logits[total_source:]
logits_target_w = logits_target[: tf.shape(target_w)[0]]
y_hat_target_w = tf.nn.softmax(logits_target_w)
# Align the target label distribution to that of the source.
expectation_ratio = tf.reduce_mean(y_hat_source_w) / tf.reduce_mean(
y_hat_target_w
)
y_tilde_target_w = tf.math.l2_normalize(
y_hat_target_w * expectation_ratio, 1
)
## 3. Relative confidence thresholding ##
row_wise_max = tf.reduce_max(y_hat_source_w, axis=-1)
final_sum = tf.reduce_mean(row_wise_max, 0)
c_tau = self.tau * final_sum
mask = tf.reduce_max(y_tilde_target_w, axis=-1) >= c_tau
## Compute losses (pay attention to the indexing) ##
source_loss = compute_loss_source(
source_labels,
final_source_logits[: tf.shape(source_w)[0]],
final_source_logits[tf.shape(source_w)[0] :],
)
target_loss = compute_loss_target(
y_tilde_target_w, logits_target[tf.shape(target_w)[0] :], mask
)
t = self.compute_mu() # Compute weight for the target loss
total_loss = source_loss + (t * target_loss)
self.current_step.assign_add(
1
) # Update current training step for the scheduler
gradients = tape.gradient(total_loss, self.model.trainable_variables)
self.optimizer.apply_gradients(zip(gradients, self.model.trainable_variables))
self.loss_tracker.update_state(total_loss)
return {"loss": self.loss_tracker.result()}
作者在论文中引入了三种改进
compute_loss_target()
中使用mask
)。在 AdaMatch 中,此阈值会进行相对调整,因此称为相对置信度阈值。有关这些方法的更多详细信息以及它们各自的贡献,请参阅论文。
关于compute_mu()
:
AdaMatch 中使用的是一个变化的标量,而不是固定的标量量。它表示目标样本贡献的损失权重。直观上,权重调度程序看起来像这样
此调度程序在前一半训练中将目标域损失的权重从 0 提高到 1。然后在后一半训练中将该权重保持在 1。
作者使用WideResNet-28-2 作为我们在此示例中使用的数据集对。以下大部分代码都参考了此脚本。请注意,以下模型在其内部包含一个缩放层,该层将像素值缩放至 [0, 1]。
def wide_basic(x, n_input_plane, n_output_plane, stride):
conv_params = [[3, 3, stride, "same"], [3, 3, (1, 1), "same"]]
n_bottleneck_plane = n_output_plane
# Residual block
for i, v in enumerate(conv_params):
if i == 0:
if n_input_plane != n_output_plane:
x = layers.BatchNormalization()(x)
x = layers.Activation("relu")(x)
convs = x
else:
convs = layers.BatchNormalization()(x)
convs = layers.Activation("relu")(convs)
convs = layers.Conv2D(
n_bottleneck_plane,
(v[0], v[1]),
strides=v[2],
padding=v[3],
kernel_initializer=INIT,
kernel_regularizer=regularizers.l2(WEIGHT_DECAY),
use_bias=False,
)(convs)
else:
convs = layers.BatchNormalization()(convs)
convs = layers.Activation("relu")(convs)
convs = layers.Conv2D(
n_bottleneck_plane,
(v[0], v[1]),
strides=v[2],
padding=v[3],
kernel_initializer=INIT,
kernel_regularizer=regularizers.l2(WEIGHT_DECAY),
use_bias=False,
)(convs)
# Shortcut connection: identity function or 1x1
# convolutional
# (depends on difference between input & output shape - this
# corresponds to whether we are using the first block in
# each
# group; see `block_series()`).
if n_input_plane != n_output_plane:
shortcut = layers.Conv2D(
n_output_plane,
(1, 1),
strides=stride,
padding="same",
kernel_initializer=INIT,
kernel_regularizer=regularizers.l2(WEIGHT_DECAY),
use_bias=False,
)(x)
else:
shortcut = x
return layers.Add()([convs, shortcut])
# Stacking residual units on the same stage
def block_series(x, n_input_plane, n_output_plane, count, stride):
x = wide_basic(x, n_input_plane, n_output_plane, stride)
for i in range(2, int(count + 1)):
x = wide_basic(x, n_output_plane, n_output_plane, stride=1)
return x
def get_network(image_size=32, num_classes=10):
n = (DEPTH - 4) / 6
n_stages = [16, 16 * WIDTH_MULT, 32 * WIDTH_MULT, 64 * WIDTH_MULT]
inputs = keras.Input(shape=(image_size, image_size, 3))
x = layers.Rescaling(scale=1.0 / 255)(inputs)
conv1 = layers.Conv2D(
n_stages[0],
(3, 3),
strides=1,
padding="same",
kernel_initializer=INIT,
kernel_regularizer=regularizers.l2(WEIGHT_DECAY),
use_bias=False,
)(x)
## Add wide residual blocks ##
conv2 = block_series(
conv1,
n_input_plane=n_stages[0],
n_output_plane=n_stages[1],
count=n,
stride=(1, 1),
) # Stage 1
conv3 = block_series(
conv2,
n_input_plane=n_stages[1],
n_output_plane=n_stages[2],
count=n,
stride=(2, 2),
) # Stage 2
conv4 = block_series(
conv3,
n_input_plane=n_stages[2],
n_output_plane=n_stages[3],
count=n,
stride=(2, 2),
) # Stage 3
batch_norm = layers.BatchNormalization()(conv4)
relu = layers.Activation("relu")(batch_norm)
# Classifier
trunk_outputs = layers.GlobalAveragePooling2D()(relu)
outputs = layers.Dense(
num_classes, kernel_regularizer=regularizers.l2(WEIGHT_DECAY)
)(trunk_outputs)
return keras.Model(inputs, outputs)
我们现在可以像这样实例化一个 Wide ResNet 模型。请注意,这里使用 Wide ResNet 的目的是使实现尽可能接近原始实现。
wrn_model = get_network()
print(f"Model has {wrn_model.count_params()/1e6} Million parameters.")
Model has 1.471226 Million parameters.
reduce_lr = keras.optimizers.schedules.CosineDecay(LEARNING_RATE, TOTAL_STEPS, 0.25)
optimizer = keras.optimizers.Adam(reduce_lr)
adamatch_trainer = AdaMatch(model=wrn_model, total_steps=TOTAL_STEPS)
adamatch_trainer.compile(optimizer=optimizer)
total_ds = tf.data.Dataset.zip((final_source_ds, final_target_ds))
adamatch_trainer.fit(total_ds, epochs=EPOCHS)
Epoch 1/10
382/382 [==============================] - 155s 392ms/step - loss: 149259583488.0000
Epoch 2/10
382/382 [==============================] - 145s 379ms/step - loss: 2.0935
Epoch 3/10
382/382 [==============================] - 145s 380ms/step - loss: 1.7237
Epoch 4/10
382/382 [==============================] - 142s 370ms/step - loss: 1.9182
Epoch 5/10
382/382 [==============================] - 141s 367ms/step - loss: 2.9698
Epoch 6/10
382/382 [==============================] - 141s 368ms/step - loss: 3.2622
Epoch 7/10
382/382 [==============================] - 141s 367ms/step - loss: 2.9034
Epoch 8/10
382/382 [==============================] - 141s 368ms/step - loss: 3.2735
Epoch 9/10
382/382 [==============================] - 141s 369ms/step - loss: 3.9449
Epoch 10/10
382/382 [==============================] - 141s 369ms/step - loss: 3.5918
<keras.callbacks.History at 0x7f16eb261e20>
# Compile the AdaMatch model to yield accuracy.
adamatch_trained_model = adamatch_trainer.model
adamatch_trained_model.compile(metrics=keras.metrics.SparseCategoricalAccuracy())
# Score on the target test set.
svhn_test = svhn_test.batch(TARGET_BATCH_SIZE).prefetch(AUTO)
_, accuracy = adamatch_trained_model.evaluate(svhn_test)
print(f"Accuracy on target test set: {accuracy * 100:.2f}%")
136/136 [==============================] - 4s 24ms/step - loss: 508.2073 - sparse_categorical_accuracy: 0.2408
Accuracy on target test set: 24.08%
随着训练的进行,此分数会提高。当使用标准分类目标训练相同的网络时,其准确率为7.20%,远低于我们使用 AdaMatch 获得的结果。您可以查看此笔记本,以了解有关超参数和其他实验细节的更多信息。
# Utility function for preprocessing the source test set.
def prepare_test_ds_source(image, label):
image = tf.image.resize_with_pad(image, RESIZE_TO, RESIZE_TO)
image = tf.tile(image, [1, 1, 3])
return image, label
source_test_ds = tf.data.Dataset.from_tensor_slices((mnist_x_test, mnist_y_test))
source_test_ds = (
source_test_ds.map(prepare_test_ds_source, num_parallel_calls=AUTO)
.batch(TARGET_BATCH_SIZE)
.prefetch(AUTO)
)
# Evaluation on the source test set.
_, accuracy = adamatch_trained_model.evaluate(source_test_ds)
print(f"Accuracy on source test set: {accuracy * 100:.2f}%")
53/53 [==============================] - 2s 24ms/step - loss: 508.2072 - sparse_categorical_accuracy: 0.9736
Accuracy on source test set: 97.36%
您可以使用这些模型权重来重现结果。