CGAN 简介与代码实战_cgan dscn

1.介绍
  原始GAN（GAN 简介与代码实战_天竺街潜水的八角的博客-CSDN博客）在理论上可以完全逼近真实数据，但它的可控性不强（生成小图片还行，生成的大图片可能是不合逻辑的），因此需要对gan加一些约束，能生成我们想要的图片，这个时候，CGAN就横空出世了，更加详细的介绍参考论文：Conditional Generative Adversarial Nets
 

2.模型结构

 公式1是原始GAN的损失函数，公式2相对于公式1多了一个条件y，这个y可以是标签和图片中需要修复的部分（比如动物）等

 如果只看公式2，很难想象到，怎样才能把y当作条件来融入网络。看下图之后，我们很容易想到，条件y和待判别的图像被拼接(concat)起来就可以达到这个效果。 

3.模型特点

使用额外信息y对模型增加条件，可以指导数据生成过程

4.代码实现 keras

class CGAN():
    def __init__(self):
        # Input shape
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        self.num_classes = 10
        self.latent_dim = 100
 
        optimizer = Adam(0.0002, 0.5)
 
        # 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 and the target label as input
        # and generates the corresponding digit of that label
        noise = Input(shape=(self.latent_dim,))
        label = Input(shape=(1,))
        img = self.generator([noise, label])
 
        # For the combined model we will only train the generator
        self.discriminator.trainable = False
 
        # The discriminator takes generated image as input and determines validity
        # and the label of that image
        valid = self.discriminator([img, label])
 
        # The combined model  (stacked generator and discriminator)
        # Trains generator to fool discriminator
        self.combined = Model([noise, label], valid)
        self.combined.compile(loss=['binary_crossentropy'],
            optimizer=optimizer)
 
    def build_generator(self):
 
        model = Sequential()
 
        model.add(Dense(256, input_dim=self.latent_dim))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(1024))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(np.prod(self.img_shape), activation='tanh'))
        model.add(Reshape(self.img_shape))
 
        model.summary()
 
        noise = Input(shape=(self.latent_dim,))
        label = Input(shape=(1,), dtype='int32')
        label_embedding = Flatten()(Embedding(self.num_classes, self.latent_dim)(label))
 
        model_input = multiply([noise, label_embedding])
        img = model(model_input)
 
        return Model([noise, label], img)
 
    def build_discriminator(self):
 
        model = Sequential()
 
        model.add(Dense(512, input_dim=np.prod(self.img_shape)))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.4))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.4))
        model.add(Dense(1, activation='sigmoid'))
        model.summary()
 
        img = Input(shape=self.img_shape)
        label = Input(shape=(1,), dtype='int32')
 
        label_embedding = Flatten()(Embedding(self.num_classes, np.prod(self.img_shape))(label))
        flat_img = Flatten()(img)
 
        model_input = multiply([flat_img, label_embedding])
 
        validity = model(model_input)
 
        return Model([img, label], validity)
 
    def train(self, epochs, batch_size=128, sample_interval=50):
 
        # Load the dataset
        (X_train, y_train), (_, _) = mnist.load_data()
 
        # Configure input
        X_train = (X_train.astype(np.float32) - 127.5) / 127.5
        X_train = np.expand_dims(X_train, axis=3)
        y_train = y_train.reshape(-1, 1)
 
        # 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 half batch of images
            idx = np.random.randint(0, X_train.shape[0], batch_size)
            imgs, labels = X_train[idx], y_train[idx]
 
            # Sample noise as generator input
            noise = np.random.normal(0, 1, (batch_size, 100))
 
            # Generate a half batch of new images
            gen_imgs = self.generator.predict([noise, labels])
 
            # Train the discriminator
            d_loss_real = self.discriminator.train_on_batch([imgs, labels], valid)
            d_loss_fake = self.discriminator.train_on_batch([gen_imgs, labels], fake)
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)
 
            # ---------------------
            #  Train Generator
            # ---------------------
 
            # Condition on labels
            sampled_labels = np.random.randint(0, 10, batch_size).reshape(-1, 1)
 
            # Train the generator
            g_loss = self.combined.train_on_batch([noise, sampled_labels], valid)
 
            # Plot the progress
            print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))
 
            # If at save interval => save generated image samples
            if epoch % sample_interval == 0:
                self.sample_images(epoch)
 
    def sample_images(self, epoch):
        r, c = 2, 5
        noise = np.random.normal(0, 1, (r * c, 100))
        sampled_labels = np.arange(0, 10).reshape(-1, 1)
 
        gen_imgs = self.generator.predict([noise, sampled_labels])
 
        # Rescale images 0 - 1
        gen_imgs = 0.5 * gen_imgs + 0.5
 
        fig, axs = plt.subplots(r, c)
        cnt = 0
        for i in range(r):
            for j in range(c):
                axs[i,j].imshow(gen_imgs[cnt,:,:,0], cmap='gray')
                axs[i,j].set_title("Digit: %d" % sampled_labels[cnt])
                axs[i,j].axis('off')
                cnt += 1
        fig.savefig("images/%d.png" % epoch)
        plt.close()