2020-09-08

---

前言

变分自编码器（Variational Autoencoder，VAE）是生成式模型（Generative Model）的一种，另一种常见的生成式模型是生成式对抗网络（Generative Adversarial Network，GAN）

---

提示：以下是本篇文章正文内容，下面案例可供参考

一、变分自编码器

Keras实现

二、原理及实现

引入库

# -*- coding: utf-8 -*-

import numpy as np
import matplotlib.pyplot as plt

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

定义一些常数

batch_size = 100
original_dim = 784
intermediate_dim = 256
latent_dim = 2
epochs = 50

encoder部分，两层全连接层，隐层表示包括均值和方差

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

Lambda层不参与训练，只参与计算，用于后面产生新的z

def sampling(args):
    z_mean, z_log_var = args
    epsilon = K.random_normal(shape=(batch_size, latent_dim), mean=0.)
    return z_mean + K.exp(z_log_var / 2) * epsilon

z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])

decoder部分，两层全连接层，x_decoded_mean为重构的输出

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)

自定义总的损失函数并编译模型

def vae_loss(x, x_decoded_mean):
    xent_loss = original_dim * objectives.binary_crossentropy(x, x_decoded_mean)
    kl_loss = -0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
    return xent_loss + kl_loss

vae = Model(x, x_decoded_mean)
vae.compile(optimizer='rmsprop', loss=vae_loss)

加载数据并训练

(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:])))

vae.fit(x_train, x_train,
        shuffle=True,
        epochs=epochs,
        batch_size=batch_size,
        validation_data=(x_test, x_test))

定义一个encoder，看看MNIST中的数据在隐层中变成了什么样子

encoder = Model(x, z_mean)

x_test_encoded = encoder.predict(x_test, batch_size=batch_size)
plt.figure(figsize=(6, 6))
plt.scatter(x_test_encoded[:, 0], x_test_encoded[:, 1], c=y_test)
plt.colorbar()
plt.show()

再定义一个生成器，从隐层到输出，用于产生新的样本

decoder_input = Input(shape=(latent_dim,))
_h_decoded = decoder_h(decoder_input)
_x_decoded_mean = decoder_mean(_h_decoded)
generator = Model(decoder_input, _x_decoded_mean)

用网格化的方法产生一些二维数据，作为新的z输入到生成器，并将生成的x展示出来

n = 20
digit_size = 28
figure = np.zeros((digit_size * n, digit_size * n))
grid_x = np.linspace(-4, 4, n)
grid_y = np.linspace(-4, 4, n)

for i, xi in enumerate(grid_x):
    for j, yi in enumerate(grid_y):
        z_sample = np.array([[yi, xi]])
        x_decoded = generator.predict(z_sample)
        digit = x_decoded[0].reshape(digit_size, digit_size)
        figure[(n - i - 1) * digit_size: (n - i) * digit_size,
               j * digit_size: (j + 1) * digit_size] = digit

plt.figure(figsize=(10, 10))
plt.imshow(figure)
plt.show()

---

三、参数理解

input_shape：即张量的shape。从前往后对应由外向内的维度。

input_length：代表序列长度，可以理解成有多少个样本

input_dim：代表张量的维度，