CGAN代码并解释代码

CGAN是一种条件生成对抗网络，它可以根据给定的条件生成具有所需特征的图像。以下是一个简单的CGAN代码示例，其中使用MNIST数据集生成手写数字图像：

首先，我们需要导入所需的库和数据集：

import tensorflow as tf
from tensorflow.keras import layers
import numpy as np
import matplotlib.pyplot as plt

# 加载MNIST数据集
(train_images, train_labels), (_, _) = tf.keras.datasets.mnist.load_data()
train_images = train_images.reshape(train_images.shape[0], 28, 28, 1).astype('float32')
train_images = (train_images - 127.5) / 127.5  # 归一化为[-1, 1]的范围

接下来，我们定义生成器和判别器模型：

# 生成器模型
def make_generator_model():
    model = tf.keras.Sequential()
    model.add(layers.Dense(7*7*256, use_bias=False, input_shape=(100,)))
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Reshape((7, 7, 256)))
    assert model.output_shape == (None, 7, 7, 256)  # 注意：batch size没有限制

    model.add(layers.Conv2DTranspose(128, (5, 5), strides=(1, 1), padding='same', use_bias=False))
    assert model.output_shape == (None, 7, 7, 128)
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(64, (5, 5), strides=(2, 2), padding='same', use_bias=False))
    assert model.output_shape == (None, 14, 14, 64)
    model.add(layers.BatchNormalization())
    model.add(layers.LeakyReLU())

    model.add(layers.Conv2DTranspose(1, (5, 5), strides=(2, 2), padding='same', use_bias=False, activation='tanh'))
    assert model.output_shape == (None, 28, 28, 1)

    return model

# 判别器模型
def make_discriminator_model():
    model = tf.keras.Sequential()
    model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',
                                     input_shape=[28, 28, 1]))
    model.add(layers.LeakyReLU())
    model.add(layers.Dropout(0.3))

    model.add(layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same'))
    model.add(layers.LeakyReLU())
    model.add(layers.Dropout(0.3))

    model.add(layers.Flatten())
    model.add(layers.Dense(1))

    return model

然后，我们定义损失函数和优化器：

# 定义损失函数和优化器
cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)

def discriminator_loss(real_output, fake_output):
    real_loss = cross_entropy(tf.ones_like(real_output), real_output)
    fake_loss = cross_entropy(tf.zeros_like(fake_output), fake_output)
    total_loss = real_loss + fake_loss
    return total_loss

def generator_loss(fake_output):
    return cross_entropy(tf.ones_like(fake_output), fake_output)

generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)

接下来，我们定义训练循环：

# 定义训练循环
@tf.function
def train_step(images, labels):
    noise = tf.random.normal([BATCH_SIZE, 100])

    with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
        generated_images = generator([noise, labels], training=True)

        real_output = discriminator([images, labels], training=True)
        fake_output = discriminator([generated_images, labels], training=True)

        gen_loss = generator_loss(fake_output)
        disc_loss = discriminator_loss(real_output, fake_output)

    gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
    gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)

    generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
    discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))

最后，我们开始训练模型，生成手写数字图像：

# 开始训练模型
EPOCHS = 50
BATCH_SIZE = 256
num_examples_to_generate = 16

# 我们将重复使用该种子（因此在动画 GIF 中更容易可视化进度）
seed = tf.random.normal([num_examples_to_generate, 100])

# 将标签与种子一起生成图像
def generate_and_save_images(model, epoch, test_input, labels):
    # 注意 training` 设定为 False
    # 因此，所有层都在推理模式下运行（batchnorm）。
    predictions = model([test_input, labels], training=False)

    fig = plt.figure(figsize=(4, 4))

    for i in range(predictions.shape[0]):
        plt.subplot(4, 4, i+1)
        plt.imshow((predictions[i, :, :, 0] + 1) / 2, cmap='gray')
        plt.axis('off')

    plt.savefig('image_at_epoch_{:04d}.png'.format(epoch))
    plt.show()

generator = make_generator_model()
discriminator = make_discriminator_model()

for epoch in range(EPOCHS):
    for i in range(train_images.shape[0] // BATCH_SIZE):
        images = train_images[i*BATCH_SIZE:(i+1)*BATCH_SIZE]
        labels = train_labels[i*BATCH_SIZE:(i+1)*BATCH_SIZE]
        train_step(images, labels)

    if epoch % 5 == 0:
        generate_and_save_images(generator, epoch, seed, np.array([0,1,2,3,4,5,6,7,8,9]))

这段代码中，我们使用了条件变量labels，它可以让我们控制生成的图像具有所需的特征，例如生成特定数字的图像。在训练循环中，我们使用了两个损失函数：判别器损失和生成器损失。在每个epoch结束时，我们生成一些手写数字图像并保存它们。