好像还挺好玩的GAN6——Keras搭建LSGAN最小二乘GAN

学习前言

据说这个大宝贝的生成效果比较好，让我试试。

什么是LSGAN

LSGAN是一种最小二乘GAN。

其主要特点为将loss函数的计算方式由交叉熵更改为均方差。

无论是判别模型的训练，还是生成模型的训练，都需要将交叉熵更改为均方差。

神经网络构建

1、Generator

生成网络的目标是输入一行正态分布随机数，生成mnist手写体图片，因此它的输入是一个N维的向量，输出一个28,28,1维的图片。

def build_generator(self):
    # --------------------------------- #
    #   生成器，输入一串随机数字
    # --------------------------------- #
    model = Sequential()

    model.add(Dense(256, input_dim=self.latent_dim))
    model.add(LeakyReLU(alpha=0.2))
    model.add(BatchNormalization(momentum=0.8))
    model.add(Dense(512))
    model.add(LeakyReLU(alpha=0.2))
    model.add(BatchNormalization(momentum=0.8))
    model.add(Dense(1024))
    model.add(LeakyReLU(alpha=0.2))
    model.add(BatchNormalization(momentum=0.8))
    model.add(Dense(np.prod(self.img_shape), activation='tanh'))
    model.add(Reshape(self.img_shape))

    noise = Input(shape=(self.latent_dim,))
    img = model(noise)

    return Model(noise, img)

2、Discriminator

判别模型的目的是根据输入的图片判断出真伪。因此它的输入一个28,28,1维的图片，输出是0到1之间的数，1代表判断这个图片是真的，0代表判断这个图片是假的。

def build_discriminator(self):
    # ----------------------------------- #
    #   评价器，对输入进来的图片进行评价
    # ----------------------------------- #
    model = Sequential()
    # 输入一张图片
    model.add(Flatten(input_shape=self.img_shape))
    model.add(Dense(512))
    model.add(LeakyReLU(alpha=0.2))
    model.add(Dense(256))
    model.add(LeakyReLU(alpha=0.2))
    # 判断真伪  
    model.add(Dense(1))

    img = Input(shape=self.img_shape)
    validity = model(img)

    return Model(img, validity)

训练思路

LSGAN的训练思路分为如下几个步骤：
1、随机选取batch_size个真实的图片。
2、随机生成batch_size个N维向量，传入到Generator中生成batch_size个虚假图片。
3、真实图片的label为1，虚假图片的label为0，将真实图片和虚假图片当作训练集传入到Discriminator中进行训练，训练的loss使用均方差。
4、将虚假图片的Discriminator预测结果与1的对比作为loss对Generator进行训练（与1对比的意思是，如果Discriminator将虚假图片判断为1，说明这个生成的图片很“真实”），这个loss同样使用均方差。

实现全部代码

from __future__ import print_function, division

from keras.datasets import mnist
from keras.layers import Input, Dense, Reshape, Flatten, Dropout
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
import matplotlib.pyplot as plt
import numpy as np
import sys
import os

class LSGAN():
    def __init__(self):
        self.img_rows = 28
        self.img_cols = 28
        self.channels = 1
        self.img_shape = (self.img_rows, self.img_cols, self.channels)
        self.latent_dim = 100

        optimizer = Adam(0.0002, 0.5)

        self.discriminator = self.build_discriminator()
        self.discriminator.compile(loss='mse',
            optimizer=optimizer,
            metrics=['accuracy'])

        self.generator = self.build_generator()

        z = Input(shape=(self.latent_dim,))
        img = self.generator(z)

        self.discriminator.trainable = False

        valid = self.discriminator(img)

        self.combined = Model(z, valid)
        self.combined.compile(loss='mse', optimizer=optimizer)

    def build_generator(self):
        # --------------------------------- #
        #   生成器，输入一串随机数字
        # --------------------------------- #
        model = Sequential()

        model.add(Dense(256, input_dim=self.latent_dim))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(1024))
        model.add(LeakyReLU(alpha=0.2))
        model.add(BatchNormalization(momentum=0.8))
        model.add(Dense(np.prod(self.img_shape), activation='tanh'))
        model.add(Reshape(self.img_shape))


        noise = Input(shape=(self.latent_dim,))
        img = model(noise)

        return Model(noise, img)

    def build_discriminator(self):
        # ----------------------------------- #
        #   评价器，对输入进来的图片进行评价
        # ----------------------------------- #
        model = Sequential()
        # 输入一张图片
        model.add(Flatten(input_shape=self.img_shape))
        model.add(Dense(512))
        model.add(LeakyReLU(alpha=0.2))
        model.add(Dense(256))
        model.add(LeakyReLU(alpha=0.2))
        # 判断真伪  
        model.add(Dense(1))

        img = Input(shape=self.img_shape)
        validity = model(img)

        return Model(img, validity)

    def train(self, epochs, batch_size=128, sample_interval=50):
        (X_train, _), (_, _) = mnist.load_data()

        X_train = (X_train.astype(np.float32) - 127.5) / 127.5
        X_train = np.expand_dims(X_train, axis=3)

        valid = np.ones((batch_size, 1))
        fake = np.zeros((batch_size, 1))

        for epoch in range(epochs):

            # --------------------------- #
            #   随机选取batch_size个图片
            #   对discriminator进行训练
            # --------------------------- #
            idx = np.random.randint(0, X_train.shape[0], batch_size)
            imgs = X_train[idx]

            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))

            gen_imgs = self.generator.predict(noise)

            d_loss_real = self.discriminator.train_on_batch(imgs, valid)
            d_loss_fake = self.discriminator.train_on_batch(gen_imgs, fake)
            d_loss = 0.5 * np.add(d_loss_real, d_loss_fake)

            # --------------------------- #
            #  训练generator
            # --------------------------- #
            noise = np.random.normal(0, 1, (batch_size, self.latent_dim))
            g_loss = self.combined.train_on_batch(noise, valid)
            print ("%d [D loss: %f, acc.: %.2f%%] [G loss: %f]" % (epoch, d_loss[0], 100*d_loss[1], g_loss))

            if epoch % sample_interval == 0:
                self.sample_images(epoch)


    def sample_images(self, epoch):
        r, c = 5, 5
        noise = np.random.normal(0, 1, (r * c, self.latent_dim))
        gen_imgs = self.generator.predict(noise)

        gen_imgs = 0.5 * gen_imgs + 0.5

        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/%d.png" % epoch)
        plt.close()


if __name__ == '__main__':
    if not os.path.exists("./images"):
        os.makedirs("./images")
    gan = LSGAN()
    gan.train(epochs=30000, batch_size=512, sample_interval=200)

实现效果为：