GAN的基本示例

GAN的基本示例
GAN的原理：

代码实现部分

import tensorflow as tf
import numpy as np
import pandas as pd
import os
from  sklearn.preprocessing import MinMaxScaler
from  tensorflow import keras
import matplotlib.pyplot as plt

# 载入数据
(x_train_all, y_train_all), (x_test, y_test) = keras.datasets.mnist.load_data()

# 划分数据集
x_train, x_valid = x_train_all[5000:], x_train_all[:5000]
y_train, y_valid = y_train_all[5000:], y_train_all[:5000]

# 归一化处理
scaler = MinMaxScaler()
x_train_scaled = scaler.fit_transform(x_train.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_test_scaled = scaler.transform(x_test.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)
x_valid_scaled = scaler.transform(x_valid.astype(np.float32).reshape(-1, 1)).reshape(-1, 28, 28, 1)

# 封装数据集
train_datasets = tf.data.Dataset.from_tensor_slices(x_train_scaled)
train_datasets = train_datasets.shuffle(x_train_scaled.shape[0]).batch(128)


# 建立模型
# 生成器模型
def generator_model():
    model = keras.Sequential()
    model.add(keras.layers.Input(shape=(100,)))

    model.add(keras.layers.Dense(256, use_bias=False))
    model.add(keras.layers.BatchNormalization())
    model.add(keras.layers.LeakyReLU())

    model.add(keras.layers.Dense(512, use_bias=False))
    model.add(keras.layers.BatchNormalization())
    model.add(keras.layers.LeakyReLU())

    model.add(keras.layers.Dense(28 * 28 * 1, use_bias=False, activation='tanh'))
    model.add(keras.layers.BatchNormalization())

    model.add(keras.layers.Reshape((28, 28, 1)))

    return model


# 判别器模型
def discriminator_model():
    model = keras.Sequential()
    model.add(keras.layers.Flatten(input_shape=(28, 28)))

    model.add(keras.layers.Dense(512, use_bias=False))
    model.add(keras.layers.BatchNormalization())
    model.add(keras.layers.LeakyReLU())

    model.add(keras.layers.Dense(256, use_bias=False))
    model.add(keras.layers.BatchNormalization())
    model.add(keras.layers.LeakyReLU())

    model.add(keras.layers.Dense(1))

    return model


# 定义损失函数
cross_entropy = tf.losses.BinaryCrossentropy(from_logits=True)


# 判别器损失
def discriminator_loss(real_output, fake_output):
    real_loss = cross_entropy(tf.ones_like(real_output), real_output)
    fake_loss = cross_entropy(tf.zeros_like(fake_output), fake_output)
    total_loss = real_loss + fake_loss
    return total_loss


# 生成器损失
def generator_loss(fake_output):
    return cross_entropy(tf.ones_like(fake_output), fake_output)


# 定义优化器
generator_optimizer = tf.keras.optimizers.Adam(1e-4)
discriminator_optimizer = tf.keras.optimizers.Adam(1e-4)

EPOCHS = 10
noise_dim = 100
num_examples_to_generate = 16
BATCH_SIZE = 256

seed = tf.random.normal([num_examples_to_generate, noise_dim])  # (16,100)

generator = generator_model()
discriminator = discriminator_model()


# 迭代训练
@tf.function
def train_step(images):
    noise = tf.random.normal([BATCH_SIZE, noise_dim])  # (256,100)

    with tf.GradientTape() as gen_tape, tf.GradientTape() as disc_tape:
        generated_images = generator(noise, training=True)

        real_output = discriminator(images, training=True)
        fake_output = discriminator(generated_images, training=True)

        gen_loss = generator_loss(fake_output)
        disc_loss = discriminator_loss(real_output, fake_output)

    gradients_of_generator = gen_tape.gradient(gen_loss, generator.trainable_variables)
    gradients_of_discriminator = disc_tape.gradient(disc_loss, discriminator.trainable_variables)

    generator_optimizer.apply_gradients(zip(gradients_of_generator, generator.trainable_variables))
    discriminator_optimizer.apply_gradients(zip(gradients_of_discriminator, discriminator.trainable_variables))


# 生成图片
def generate_and_save_images(generator_model, epoch, seed):
    pred = generator_model(seed, training=True)

    plt.figure(figsize=(4, 4))

    for i in range(pred.shape[0]):
        plt.subplot(4, 4, i + 1)
        plt.imshow((pred[i, :, :, 0] + 1) / 2, cmap='gray')
        plt.axis('off')

    # plt.savefig('image_at_epoch_{:04d}.png'.format(epoch))
    plt.show()


# 训练
def train(train_datasets, epochs):
    for epoch in range(epochs):
        for image_batch in train_datasets:
            train_step(image_batch)
            print('.', end='')
        print()

    generate_and_save_images(generator, epochs, seed)


train(train_datasets, EPOCHS)