在 tf.keras 中正确设置 GAN 实现中的 .trainable 变量

Question

在一个GAN的实现中，我对tf.keras.model的.trainable语句感到困惑。

给出以下代码片段（摘自 this repo）：

class GAN():

    def __init__(self):

        ...

        # Build and compile the discriminator
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss='binary_crossentropy',
            optimizer=optimizer,
            metrics=['accuracy'])

        # Build the generator
        self.generator = self.build_generator()

        # The generator takes noise as input and generates imgs
        z = Input(shape=(self.latent_dim,))
        img = self.generator(z)

        # For the combined model we will only train the generator
        self.discriminator.trainable = False

        # The discriminator takes generated images as input and determines validity
        validity = self.discriminator(img)

        # The combined model  (stacked generator and discriminator)
        # Trains the generator to fool the discriminator
        self.combined = Model(z, validity)
        self.combined.compile(loss='binary_crossentropy', optimizer=optimizer)

    def build_generator(self):

        ...

        return Model(noise, img)

    def build_discriminator(self):

        ...

        return Model(img, validity)

    def train(self, epochs, batch_size=128, sample_interval=50):

        # Load the dataset
        (X_train, _), (_, _) = mnist.load_data()

        # Adversarial ground truths
        valid = np.ones((batch_size, 1))
        fake = np.zeros((batch_size, 1))

        for epoch in range(epochs):

            # ---------------------
            #  Train Discriminator
            # ---------------------

            # Select a random batch of images
            idx = np.random.randint(0, X_train.shape[0], batch_size)
            imgs = X_train[idx]

            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))

            # Generate a batch of new images
            gen_imgs = self.generator.predict(noise)

            # Train the discriminator
            d_loss_real = self.discriminator.train_on_batch(imgs, valid)
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

            # ---------------------
            #  Train Generator
            # ---------------------

            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))

            # Train the generator (to have the discriminator label samples as valid)
            g_loss = self.combined.train_on_batch(noise, valid)

在模型定义期间 self.combined 鉴别器的权重设置为 self.discriminator.trainable = False 但从未重新打开。

不过，在训练循环期间，判别器的权重将针对以下行发生变化：

# Train the discriminator
d_loss_real = self.discriminator.train_on_batch(imgs, valid)
d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)
d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

并将在以下期间保持不变：

# Train the generator (to have the discriminator label samples as valid)
g_loss = self.combined.train_on_batch(noise, valid)

这是我没想到的。

当然这是训练 GAN 的正确（迭代）方式，但我不明白为什么我们不必通过 self.discriminator.trainable = True 就可以对鉴别器进行一些训练。

那就太好了如果有人对此有解释，我想这是理解的关键点。

Answer 1

当您对 github 存储库中的代码有疑问时，检查问题（打开的和关闭的）通常是个好主意。 This issue 解释了为什么将标志设置为 False。它说，

Since self.discriminator.trainable = False is set after the discriminator is compiled, it will not affect the training of the discriminator. However since it is set before the combined model is compiled the discriminator layers will be frozen when the combined model is trained.

还谈到了freezing keras layers。

在 tf.keras 中正确设置 GAN 实现中的 .trainable 变量

Set .trainable variable in GAN implementation in tf.keras properly

python

tensorflow

tf.keras

tensorflow2.0