gan（对抗生成网络）代码详解（一）-gan

 

from __future__ import print_function, division

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten, Dropout
from keras.layers import BatchNormalization, Activation, 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 sys

import numpy as np

class GAN():
    def __init__(self):
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        self.latent_dim = 100

        optimizer = Adam(0.0002, 0.5)

        # Build and compile the discriminator
        # 建立和编译判别器
        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss='binary_crossentropy',
            optimizer=optimizer,
            metrics=['accuracy'])

        # Build the generator
        # 建立生成器
        self.generator = self.build_generator()

        # The generator takes noise as input and generates imgs
        # 生成器输入随机数值（噪声）生成图片
        z = Input(shape=(self.latent_dim,))
        img = self.generator(z)

        # For the combined model we will only train the generator
        # 联合模型，只训练生成器
        self.discriminator.trainable = False

        # The discriminator takes generated images as input and determines validity
        # 判别器以生成的图片为输入判别有效性
        validity = self.discriminator(img)

        # The combined model  (stacked generator and discriminator)
        # 联合模型（叠加生成器和判别器）
        # Trains the generator to fool the discriminator
        # 训练生成器欺骗判别器
        self.combined = Model(z, validity)
        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,))
        img = model(noise)

        return Model(noise, img)

    def build_discriminator(self):

        model = Sequential()

        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(256))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(1, activation='sigmoid'))
        model.summary()

        img = Input(shape=self.img_shape)
        validity = model(img)

        return Model(img, validity)

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

        # Load the dataset
        # 加载数据
        (X_train, _), (_, _) = mnist.load_data()

        # Rescale -1 to 1
        # 数据缩放到-1至1之间
        X_train = X_train / 127.5 - 1.
        X_train = np.expand_dims(X_train, axis=3)

        # Adversarial ground truths
        # 对抗性的基本事实
        valid = np.ones((batch_size, 1)) # 32行1列，每个值都是1
        fake = np.zeros((batch_size, 1)) # 32行1列，每个值都是0

        for epoch in range(epochs):

            # ---------------------
            #  Train Discriminator 训练判别器
            # ---------------------

            # Select a random batch of images
            # 随机选择一批图像
            idx = np.random.randint(0, X_train.shape[0], batch_size) # X_train.shape  （6000,28,28,1）
            imgs = X_train[idx]

            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))

            # Generate a batch of new images
            # 随机生成一批图像
            gen_imgs = self.generator.predict(noise)

            # Train the discriminator
            # 训练判别器
            d_loss_real = self.discriminator.train_on_batch(imgs, valid)
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

            # ---------------------
            #  Train Generator 训练生成器
            # ---------------------

            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))

            # Train the generator (to have the discriminator label samples as valid)
            # 训练生成器（使判别器标签样本有效）
            g_loss = self.combined.train_on_batch(noise, valid)

            # Plot the progress
            # 规划进度
            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
            # 如果在保证图像间隔 => 保存生成的图像样本
            if epoch % sample_interval == 0:
                self.sample_images(epoch)

    def sample_images(self, epoch):
        r, c = 5, 5
        noise = np.random.normal(0, 1, (r * c, self.latent_dim))
        gen_imgs = self.generator.predict(noise)

        # Rescale images 0 - 1
        # 数据缩放到-1至1之间
        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].axis('off')
                cnt += 1
        fig.savefig("images/%d.png" % epoch)
        plt.close()


if __name__ == '__main__':
    gan = GAN()
    gan.train(epochs=30000, batch_size=32, sample_interval=200)

 

代码解释

from __future__ import print_function, division

在开头加上from __future__ import print_function, division这句之后，即使在python2.X，使用print、division就得像python3.X那样加括号使用。python2.X中print不需要括号，而在python3.X中则需要。

详解：

https://blog.csdn.net/xiaotao_1/article/details/79460365

https://blog.csdn.net/feixingfei/article/details/7081446