代码实现

from __future__ import print_function

import numpy as np
import matplotlib.pyplot as plt
from scipy.stats import norm

from keras.layers import Input, Dense, Lambda
from keras.models import Model
from keras import backend as K
from keras.datasets import mnist


batch_size = 100
original_dim = 784
latent_dim = 2 # 隐变量取2维只是为了方便后面画图
intermediate_dim = 256
epochs = 50


# 加载MNIST数据集
(x_train, y_train_), (x_test, y_test_) = mnist.load_data()
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))


x = Input(shape=(original_dim,))
h = Dense(intermediate_dim, activation='relu')(x)

# 算p(Z|X)的均值和方差
z_mean = Dense(latent_dim)(h)
z_log_var = Dense(latent_dim)(h)

# 重参数技巧
def sampling(args):
    z_mean, z_log_var = args
    epsilon = K.random_normal(shape=K.shape(z_mean))
    return z_mean + K.exp(z_log_var / 2) * epsilon

# 重参数层，相当于给输入加入噪声
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])

# 解码层，也就是生成器部分
decoder_h = Dense(intermediate_dim, activation='relu')
decoder_mean = Dense(original_dim, activation='sigmoid')
h_decoded = decoder_h(z)
x_decoded_mean = decoder_mean(h_decoded)

# 建立模型
vae = Model(x, x_decoded_mean)

# xent_loss是重构loss，kl_loss是KL loss
xent_loss = K.sum(K.binary_crossentropy(x, x_decoded_mean), axis=-1)
kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
vae_loss = K.mean(xent_loss + kl_loss)

# add_loss是新增的方法，用于更灵活地添加各种loss
vae.add_loss(vae_loss)
vae.compile(optimizer='rmsprop')
vae.summary()

vae.fit(x_train,
        shuffle=True,
        epochs=epochs,
        batch_size=batch_size,
        validation_data=(x_test, None))

引用

代码
变分自编码器VAE：原来是这么一回事