GAN生成对抗网络-CGAN原理与基本实现-条件生成对抗网络04

CGAN - 条件GAN

原始GAN的缺点

代码实现

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

gpu = tf.config.experimental.list_physical_devices(device_type='GPU')
tf.config.experimental.set_memory_growth(gpu[0], True)

import tensorflow.keras.datasets.mnist as mnist

(train_image, train_label), (_, _) = mnist.load_data()

train_image = train_image / 127.5  - 1

train_image = np.expand_dims(train_image, -1)

train_image.shape

dataset = tf.data.Dataset.from_tensor_slices((train_image, train_label))

AUTOTUNE = tf.data.experimental.AUTOTUNE

BATCH_SIZE = 256
image_count = train_image.shape[0]
noise_dim = 50

dataset = dataset.shuffle(image_count).batch(BATCH_SIZE)

def generator_model():
    seed = layers.Input(shape=((noise_dim,))) # 输入 形状长度为50的向量
    label = layers.Input(shape=(()))# 形状为空
        # 输入维度： 因0-9一共10个字符所以长度为10  映射成长度为50 输入序列的长度为1    
    x = layers.Embedding(10, 50, input_length=1)(label)#嵌入层将正整数（下标）转换为具有固定大小的向量
    x = layers.Flatten()(x)
    x = layers.concatenate([seed, x])# 与输入的seed合并
    x = layers.Dense(3*3*128, use_bias=False)(x)# 使用dense层转换成形状3*3通道128 的向量 不使用偏值
    x = layers.Reshape((3, 3, 128))(x) # reshape成3*3*128 
    x = layers.BatchNormalization()(x)# 批标准化
    x = layers.ReLU()(x) # 使用relu激活x 
    
    x = layers.Conv2DTranspose(64, (3, 3), strides=(2, 2), use_bias=False)(x)# 反卷积64个卷积核 卷积核大小（3*3） 跨度2
    x = layers.BatchNormalization()(x)# 批标准化
    x = layers.ReLU()(x)  #使用relu激活x   #  7*7
# 反卷积64个卷积核 卷积核大小（3*3） 跨度2  填充方式same 不适用偏值
    x = layers.Conv2DTranspose(32, (3, 3), strides=(2, 2), padding='same', use_bias=False)(x)
    x = layers.BatchNormalization()(x)
    x = layers.ReLU()(x)    #   14*14

    x = layers.Conv2DTranspose(1, (3, 3), strides=(2, 2), padding='same', use_bias=False)(x)
    x = layers.Activation('tanh')(x)
    
    model = tf.keras.Model(inputs=[seed,label], outputs=x)  
# 创建模型    
    return model

def discriminator_model():
    image = tf.keras.Input(shape=((28,28,1)))
    label = tf.keras.Input(shape=(()))
    
    x = layers.Embedding(10, 28*28, input_length=1)(label)
    x = layers.Reshape((28, 28, 1))(x)
    x = layers.concatenate([image, x])
    
    x = layers.Conv2D(32, (3, 3), strides=(2, 2), padding='same', use_bias=False)(x)
    x = layers.BatchNormalization()(x)
    x = layers.LeakyReLU()(x)
    x = layers.Dropout(0.5)(x)
    
    x = layers.Conv2D(32*2, (3, 3), strides=(2, 2), padding='same', use_bias=False)(x)
    x = layers.BatchNormalization()(x)
    x = layers.LeakyReLU()(x)
    x = layers.Dropout(0.5)(x)
    
    x = layers.Conv2D(32*4, (3, 3), strides=(2, 2), padding='same', use_bias=False)(x)
    x = layers.BatchNormalization()(x)
    x = layers.LeakyReLU()(x)
    x = layers.Dropout(0.5)(x)
    
    x = layers.Flatten()(x)
    x1 = layers.Dense(1)(x)
    
    model = tf.keras.Model(inputs=[image, label], outputs=x1)
    return model

generator = generator_model()

discriminator = discriminator_model()

binary_cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)
category_cross_entropy = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

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

def generator_loss(fake_output):
    fake_loss = binary_cross_entropy(tf.ones_like(fake_output), fake_output)
    return fake_loss

generator_optimizer = tf.keras.optimizers.Adam(1e-5)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-5)

@tf.function
def train_step(images, labels):
    batchsize = labels.shape[0]
    noise = tf.random.normal([batchsize, noise_dim])
    
    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))

noise_dim = 50
num = 10
noise_seed = tf.random.normal([num, noise_dim])
cat_seed = np.random.randint(0, 10, size=(num, 1))
print(cat_seed.T)

def generate_images(model, test_noise_input, test_cat_input, epoch):
    print('Epoch:', epoch+1)
  # Notice `training` is set to False.
  # This is so all layers run in inference mode (batchnorm).
    predictions = model((test_noise_input, test_cat_input), training=False)
    predictions = tf.squeeze(predictions)
    fig = plt.figure(figsize=(10, 1))

    for i in range(predictions.shape[0]):
        plt.subplot(1, 10, i+1)
        plt.imshow((predictions[i, :, :] + 1)/2)
        plt.axis('off')

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

def train(dataset, epochs):
    for epoch in range(epochs):
        for image_batch, label_batch in dataset:
            train_step(image_batch, label_batch)
        if epoch%10 == 0:
            generate_images(generator, noise_seed, cat_seed, epoch)
    generate_images(generator, noise_seed, cat_seed, epoch)

EPOCHS = 200

train(dataset, EPOCHS)