gan python实现，100行代码以内

好的，以下是一个简单的 GAN（生成对抗网络）的 Python 实现，代码不到 100 行：

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt

# 生成器
def generator(z, reuse=None):
    with tf.variable_scope('gen', reuse=reuse):
        hidden1 = tf.layers.dense(inputs=z, units=128, activation=tf.nn.leaky_relu)
        hidden2 = tf.layers.dense(inputs=hidden1, units=128, activation=tf.nn.leaky_relu)
        output = tf.layers.dense(inputs=hidden2, units=784, activation=tf.nn.tanh)
        return output

# 判别器
def discriminator(X, reuse=None):
    with tf.variable_scope('dis', reuse=reuse):
        hidden1 = tf.layers.dense(inputs=X, units=128, activation=tf.nn.leaky_relu)
        hidden2 = tf.layers.dense(inputs=hidden1, units=128, activation=tf.nn.leaky_relu)
        logits = tf.layers.dense(inputs=hidden2, units=1)
        output = tf.sigmoid(logits)
        return output, logits

# 输入
real_images = tf.placeholder(tf.float32, shape=[None, 784])
z = tf.placeholder(tf.float32, shape=[None, 100])

# 生成器生成样本
G = generator(z)

# 判别器判别真实样本和生成样本
D_output_real, D_logits_real = discriminator(real_images)
D_output_fake, D_logits_fake = discriminator(G, reuse=True)

# 损失函数
def loss_func(logits_in, labels_in):
    return tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=logits_in, labels=labels_in))

D_real_loss = loss_func(D_logits_real, tf.ones_like(D_logits_real) * 0.9)
D_fake_loss = loss_func(D_logits_fake, tf.zeros_like(D_logits_fake))

D_loss = D_real_loss + D_fake_loss
G_loss = loss_func(D_logits_fake, tf.ones_like(D_logits_fake))

# 优化器
lr = 0.001

tvars = tf.trainable_variables()

D_vars = [var for var in tvars if 'dis' in var.name]
G_vars = [var for var in tvars if 'gen' in var.name]

D_trainer = tf.train.AdamOptimizer(lr).minimize(D_loss, var_list=D_vars)
G_trainer = tf.train.AdamOptimizer(lr).minimize(G_loss, var_list=G_vars)

# 训练
batch_size = 100
epochs = 100

init = tf.global_variables_initializer()

samples = []

with tf.Session() as sess:
    sess.run(init)

    for epoch in range(epochs):

        num_batches = mnist.train.num_examples // batch_size

        for i in range(num_batches):

            batch = mnist.train.next_batch(batch_size)

            batch_images = batch[0].reshape((batch_size, 784))
            batch_images = batch_images * 2 - 1

            batch_z = np.random.uniform(-1, 1, size=(batch_size, 100))

            _ = sess.run(D_trainer, feed_dict={real_images: batch_images, z: batch_z})
            _ = sess.run(G_trainer, feed_dict={z: batch_z})

        print("Epoch: ", epoch)

        sample_z = np.random.uniform(-1, 1, size=(1, 100))
        gen_sample = sess.run(generator(z, reuse=True), feed_dict={z: sample_z})

        samples.append(gen_sample)

# 可视化生成结果
plt.imshow(samples[0].reshape(28, 28), cmap='Greys')
plt.show()

这个实现使用 TensorFlow 框架，生成器和判别器都是简单的全连接层，输入是 28x28 的 MNIST 图像，随机噪声采用均匀分布。训练过程中使用 Adam 优化器，损失函数是交叉熵。最终生成的图像可以用 Matplotlib 进行可视化。