【Tensorflow+Keras】keras实现条件生成对抗网络DCGAN--以Minis和fashion_mnist数据集为例

Myth丶恋晨 2023-01-21 11:23 146阅读 0赞

# 1 引言 #

条件生成对抗网络(Conditional Generative Adversarial Nets，简称CGAN)是GAN的改进。

> 举例如图所示，如果使用Minist数据集
> 
>  *  在GAN中，在训练时，随机初始化一个和图片大小一致的矩阵和原始图片的矩阵进行博弈，产生一个新的类似于原始图片的网络。
>  *  在Conditional GAN中，在训练时，会同时输入label，告诉当前网络生成的图片是数字8，而不是生成其他数字的图片

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzkzNTY5Ng_size_16_color_FFFFFF_t_70_pic_center]

图1 GAN原理图

![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzkzNTY5Ng_size_16_color_FFFFFF_t_70_pic_center 1]

图2 Conditional GAN原理图

# 2 实现 #

[Github源码][Github]

## Mian.py ##

指定条件即条件输入是Label

import tensorflow as tf
    from tensorflow.keras.datasets import fashion_mnist,mnist
    import utils
    from models import build_discriminator_model,build_generator_model
    import numpy as np
    
    # 图片维度
    noise_dim = 100
    # 学习率
    learning_rate = 1e-4
    # 交叉熵用来计算生成器Generator和鉴别器Disctiminator的损失函数
    cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=True)
    # 指定使用哪个数据集
    dataset = 'fashion_mnist'
    if dataset == 'mnist':
        (X_train, y_train), (X_test, y_test) = mnist.load_data()
    if dataset == 'fashion_mnist':
        (X_train, y_train), (X_test, y_test) = fashion_mnist.load_data()
    else:
        raise RuntimeError('Dataset not found')
    # 数据标准化
    X_train, X_test = utils.normalize(X_train, X_test)
    # 初始化G和D
    discriminator = build_discriminator_model()
    generator = build_generator_model()
    # 数据标准化
    def normalize(train, test):
      # convert from integers to floats
      train_norm = train.astype('float32')
      test_norm = test.astype('float32')
      # normalize to range 0-1
      train_norm = train_norm / 255.0
      test_norm = test_norm / 255.0
      # return normalized images
      return train_norm, test_norm
    
    # 生成器和鉴别器的优化器
    generator_optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-4)
    discriminator_optimizer = tf.keras.optimizers.Adam(learning_rate = 1e-4)
    
    # 鉴别器的损失函数
    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
    # 生成器的损失函数
    def generator_loss(fake_output):
        return cross_entropy(tf.ones_like(fake_output), fake_output)
    # 保存模型
    def save_models(epochs, learning_rate):
        generator.save(f'generator-epochs-{epochs}-learning_rate-{learning_rate}.h5')
        discriminator.save(f'discriminator-epochs-{epochs}-learning_rate-{learning_rate}.h5')
    
    # 训练
    tf.function
    def train_step(batch_size=512):
        # 随机产生一组下标，从训练数据中随机抽取训练集
        idx = np.random.randint(0, X_train.shape[0], batch_size)
        # 随机抽取训练集
        Xtrain, labels = X_train[idx], y_train[idx]
        with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
            # 随机初始化一个和图片大小的矩阵
            z = np.random.normal(0, 1, size=(batch_size, noise_dim))
            # 经过生成器，产生一个图片。并指定条件是label，把label嵌入到图片中
            generated_images = generator([z, labels], training=True)
            real_output = discriminator([Xtrain, 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)
        # 打印G和D的损失函数
        tf.print(f'Genrator loss: {gen_loss} Discriminator loss: {disc_loss}')
        gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
        gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)
        # 更新梯度
        generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
        discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))
    if __name__  =="__main__":
        epochs = 100
        for epoch in range(1, epochs + 1):
            print(f'Epoch {epoch}/{epochs}')
            train_step()
            if epoch % 500 == 0:
                save_models(epoch, learning_rate)

## Model.py ##

模型采用深度卷卷积的GAN网络结构

import tensorflow as tf
    from tensorflow.keras import layers
    from tensorflow.keras.models import Sequential, Model
    import numpy as np
    
    WIDTH, HEIGHT = 28, 28
    num_classes = 10
    img_channel = 1
    img_shape = (WIDTH, HEIGHT, img_channel)
    noise_dim = 100
    
    def build_generator_model():
        model = tf.keras.Sequential()
    
        model.add(layers.Dense(7*7*256, use_bias=False,input_shape=(noise_dim,)))
        model.add(layers.BatchNormalization())
        model.add(layers.LeakyReLU())
    
        model.add(layers.Reshape((7, 7, 256)))
    
        model.add(layers.Conv2DTranspose(128, (1, 1), strides=(1, 1), padding='same', use_bias=False))
        model.add(layers.BatchNormalization())
        model.add(layers.LeakyReLU())
    
        model.add(layers.Conv2DTranspose(64, (3, 3), strides=(2, 2), padding='same', use_bias=False))
        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'))
    
        z = layers.Input(shape=(noise_dim,))
        label = layers.Input(shape=(1,))
     
        label_embedding = layers.Embedding(num_classes, noise_dim, input_length = 1)(label)
        label_embedding = layers.Flatten()(label_embedding)
        joined = layers.multiply([z, label_embedding])
    
        img = model(joined)
        return Model([z, label], img)
    
    def build_discriminator_model():
        model = tf.keras.Sequential()
        model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',
                                          input_shape=[28, 28, 2]))
        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))
     
        img = layers.Input(shape=(img_shape))
        label = layers.Input(shape=(1,))
     
        label_embedding = layers.Embedding(input_dim=num_classes, output_dim=np.prod(img_shape), input_length = 1)(label)
        label_embedding = layers.Flatten()(label_embedding)
        label_embedding = layers.Reshape(img_shape)(label_embedding)
     
        concat = layers.Concatenate(axis=-1)([img, label_embedding])
        prediction = model(concat)
        return Model([img, label], prediction)

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzkzNTY5Ng_size_16_color_FFFFFF_t_70_pic_center]: /images/20221020/bf9bb025230943b89c596354eb0874c3.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3dlaXhpbl80MzkzNTY5Ng_size_16_color_FFFFFF_t_70_pic_center 1]: /images/20221020/bd12da600d534215a399c400899ac959.png
[Github]: https://github.com/823316627bandeng/Conditional-GANs-CGANsv