条件DCGAN（2019/09/10）

最近看到keras的官方GAN代码中有CGAN（全连接层）和卷积GAN(DCGAN),但他并没有给出“条件卷积GAN”，预测就把这两者结合了一下。虽然很多人用其他框架（e.g.TensorFlow）写出了条件卷积GAN，但代码没有keras简洁，作为keras爱好者，就做了简单地结合就完成了。

from __future__ import print_function, division

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten, Dropout, multiply
from keras.layers import BatchNormalization, Activation, Embedding,ZeroPadding2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.convolutional import UpSampling2D, Conv2D
from keras.models import Sequential, Model
from keras.optimizers import Adam

import matplotlib.pyplot as plt

import numpy as np

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

        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(14*14*32, input_dim=np.prod(self.img_shape)))
        model.add(Reshape((14, 14, 32)))
        model.add(Conv2D(64, kernel_size=3, strides=2, padding="same"))
        model.add(ZeroPadding2D(padding=((0,1),(0,1))))
        model.add(BatchNormalization(momentum=0.8))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Conv2D(128, kernel_size=3, strides=2, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Conv2D(256, kernel_size=3, strides=1, padding="same"))
        model.add(BatchNormalization(momentum=0.8))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dropout(0.25))
        model.add(Flatten())
        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) #获取标签0，1，2，3，4，5，6，7，8，9。当然你可以把标签换成全部是1，这样子后续产生的数字也全是1

        gen_imgs = self.generator.predict([noise, sampled_labels])

        # Rescale images 0 - 1
        gen_imgs = 0.5 * gen_imgs + 0.5

        n = 10  # 根据标签，产生对应的数字。
        plt.figure(figsize=(10, 2))
        for i in range(n):
            ax = plt.subplot(1, n, i + 1)
            plt.imshow(gen_imgs[i].reshape(28, 28))
            plt.gray()
            ax.get_xaxis().set_visible(False)
            ax.get_yaxis().set_visible(False)
        plt.show()
        plt.close()

if __name__ == '__main__':
    cdcgan = CDCGAN()
    cdgan.train(epochs=2000, batch_size=32, sample_interval=100)

参考的两个代码：

1.　　https://github.com/eriklindernoren/Keras-GAN/blob/master/dcgan/dcgan.py

2.　　https://github.com/eriklindernoren/Keras-GAN/blob/master/cgan/cgan.py