python实现GAN

GAN（Generative Adversarial Networks）是一种生成式模型，通过训练生成器和判别器两个模型，实现生成与真实数据相似的数据样本。下面是一个简单的Python实现GAN的示例代码：

import numpy as np
import matplotlib.pyplot as plt

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten
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

# 定义生成器模型
def build_generator():

    model = Sequential()

    model.add(Dense(128 * 7 * 7, activation="relu", input_dim=100))
    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(1, kernel_size=3, padding="same"))
    model.add(Activation("tanh"))

    noise = Input(shape=(100,))
    img = model(noise)

    return Model(noise, img)

# 定义判别器模型
def build_discriminator():

    model = Sequential()

    model.add(Conv2D(32, kernel_size=3, strides=2, input_shape=(28, 28, 1), padding="same"))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Dropout(0.25))
    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'))

    img = Input(shape=(28, 28, 1))
    validity = model(img)

    return Model(img, validity)

# 训练GAN模型
def train_gan(epochs, batch_size):

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

    # 归一化数据
    X_train = X_train / 127.5 - 1.
    X_train = np.expand_dims(X_train, axis=3)

    # 构建判别器和生成器
    discriminator = build_discriminator()
    discriminator.compile(loss='binary_crossentropy', optimizer=Adam(0.0002, 0.5), metrics=['accuracy'])
    generator = build_generator()

    # 构造GAN模型
    z = Input(shape=(100,))
    img = generator(z)
    validity = discriminator(img)
    combined = Model(z, validity)
    combined.compile(loss='binary_crossentropy', optimizer=Adam(0.0002, 0.5))

    # 训练GAN模型
    for epoch in range(epochs):

        # 训练判别器
        idx = np.random.randint(0, X_train.shape[0], batch_size)
        imgs = X_train[idx]
        noise = np.random.normal(0, 1, (batch_size, 100))
        gen_imgs = generator.predict(noise)

        d_loss_real = discriminator.train_on_batch(imgs, np.ones((batch_size, 1)))
        d_loss_fake = discriminator.train_on_batch(gen_imgs, np.zeros((batch_size, 1)))
        d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

        # 训练生成器
        noise = np.random.normal(0, 1, (batch_size, 100))
        g_loss = combined.train_on_batch(noise, np.ones((batch_size, 1)))

        # 打印损失
        print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))

        # 每100个epoch保存一次生成的图片
        if epoch % 100 == 0:
            save_imgs(generator, epoch)

# 保存生成的图片
def save_imgs(generator, epoch):
    r, c = 5, 5
    noise = np.random.normal(0, 1, (r * c, 100))
    gen_imgs = generator.predict(noise)

    # 将生成的图片转换为0-1之间的值
    gen_imgs = 0.5 * gen_imgs + 0.5

    # 绘制生成的图片
    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/mnist_%d.png" % epoch)
    plt.close()

# 执行GAN模型训练
train_gan(epochs=20000, batch_size=32)

上述代码中，我们使用MNIST数据集来训练GAN模型。首先，我们定义了一个生成器模型和一个判别器模型，然后使用这两个模型构建了一个GAN模型。在训练过程中，我们首先训练判别器，然后训练生成器，最后将两个模型结合在一起进行训练。在训练过程中，我们每隔100个epoch保存一次生成的图片。