InfoGAN 简介与代码实战

1.介绍

  在原始gan（GAN 简介与代码实战）中，生成数据的来源一般是一个固定分布噪声z，z可以生成不同的图片，z代表着很多意思，我们无法知道z的那个维度代表什么（比如在生成数字手写图片的时候，0维度是否代表笔画的风格，我们不得而知），z是不可解释的。为了解决这个问题，InfoGAN就横空出世了，更加详细的内容参见论文：Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets

 

2.模型结构

  网络是基于DC-GAN（Deep Convolutional GAN）的，G和D都由CNN构成。在此基础上，Q和D共享卷积网络，然后分别通过各自的全连接层输出不同的内容：Q输出对应于生成图片的c'（与之对应的c是可以控制图片的生成，比如生成什么数字），D则仍然判别真伪。

 

3.模型特点

      相对于原始gan，作者将Z分成z（固定分布噪声）和c（一些隐变量信息，比如笔画风格，字体大小等），损失函数里面用到互信息，使得隐变量c与生成的变量G(z,c)拥有尽可能多的共同信息。

 

 4.代码实现keras

class INFOGAN():
    def __init__(self):
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.num_classes = 10
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        self.latent_dim = 72


        optimizer = Adam(0.0002, 0.5)
        losses = ['binary_crossentropy', self.mutual_info_loss]

        # Build and the discriminator and recognition network
        self.discriminator, self.auxilliary = self.build_disk_and_q_net()

        self.discriminator.compile(loss=['binary_crossentropy'],
            optimizer=optimizer,
            metrics=['accuracy'])

        # Build and compile the recognition network Q
        self.auxilliary.compile(loss=[self.mutual_info_loss],
            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
        gen_input = Input(shape=(self.latent_dim,))
        img = self.generator(gen_input)

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

        # The discriminator takes generated image as input and determines validity
        valid = self.discriminator(img)
        # The recognition network produces the label
        target_label = self.auxilliary(img)

        # The combined model  (stacked generator and discriminator)
        self.combined = Model(gen_input, [valid, target_label])
        self.combined.compile(loss=losses,
            optimizer=optimizer)


    def build_generator(self):

        model = Sequential()

        model.add(Dense(128 * 7 * 7, activation="relu", input_dim=self.latent_dim))
        model.add(Reshape((7, 7, 128)))
        model.add(BatchNormalization(momentum=0.8))
        model.add(UpSampling2D())
        model.add(Conv2D(128, kernel_size=3, padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(UpSampling2D())
        model.add(Conv2D(64, kernel_size=3, padding="same"))
        model.add(Activation("relu"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(self.channels, kernel_size=3, padding='same'))
        model.add(Activation("tanh"))

        gen_input = Input(shape=(self.latent_dim,))
        img = model(gen_input)

        model.summary()

        return Model(gen_input, img)


    def build_disk_and_q_net(self):

        img = Input(shape=self.img_shape)

        # Shared layers between discriminator and recognition network
        model = Sequential()
        model.add(Conv2D(64, kernel_size=3, strides=2, input_shape=self.img_shape, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
        model.add(ZeroPadding2D(padding=((0,1),(0,1))))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(256, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Conv2D(512, kernel_size=3, strides=2, padding="same"))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Flatten())

        img_embedding = model(img)

        # Discriminator
        validity = Dense(1, activation='sigmoid')(img_embedding)

        # Recognition
        q_net = Dense(128, activation='relu')(img_embedding)
        label = Dense(self.num_classes, activation='softmax')(q_net)

        # Return discriminator and recognition network
        return Model(img, validity), Model(img, label)


    def mutual_info_loss(self, c, c_given_x):
        """The mutual information metric we aim to minimize"""
        eps = 1e-8
        conditional_entropy = K.mean(- K.sum(K.log(c_given_x + eps) * c, axis=1))
        entropy = K.mean(- K.sum(K.log(c + eps) * c, axis=1))

        return conditional_entropy + entropy

    def sample_generator_input(self, batch_size):
        # Generator inputs
        sampled_noise = np.random.normal(0, 1, (batch_size, 62))
        sampled_labels = np.random.randint(0, self.num_classes, batch_size).reshape(-1, 1)
        sampled_labels = to_categorical(sampled_labels, num_classes=self.num_classes)

        return sampled_noise, sampled_labels

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

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

        # Rescale -1 to 1
        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 = X_train[idx]

            # Sample noise and categorical labels
            sampled_noise, sampled_labels = self.sample_generator_input(batch_size)
            gen_input = np.concatenate((sampled_noise, sampled_labels), axis=1)

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

            # Train on real and generated data
            d_loss_real = self.discriminator.train_on_batch(imgs, valid)
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)

            # Avg. loss
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

            # ---------------------
            #  Train Generator and Q-network
            # ---------------------

            g_loss = self.combined.train_on_batch(gen_input, [valid, sampled_labels])

            # Plot the progress
            print ("%d [D loss: %.2f, acc.: %.2f%%] [Q loss: %.2f] [G loss: %.2f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss[1], g_loss[2]))

            # If at save interval => save generated image samples
            if epoch % sample_interval == 0:
                self.sample_images(epoch)

    def sample_images(self, epoch):
        r, c = 10, 10

        fig, axs = plt.subplots(r, c)
        for i in range(c):
            sampled_noise, _ = self.sample_generator_input(c)
            label = to_categorical(np.full(fill_value=i, shape=(r,1)), num_classes=self.num_classes)
            gen_input = np.concatenate((sampled_noise, label), axis=1)
            gen_imgs = self.generator.predict(gen_input)
            gen_imgs = 0.5 * gen_imgs + 0.5
            for j in range(r):
                axs[j,i].imshow(gen_imgs[j,:,:,0], cmap='gray')
                axs[j,i].axis('off')
        fig.savefig("images/%d.png" % epoch)
        plt.close()