MINST数据经常被用来训练一些简单的模型。
今天我们就使用Mnist数据集来训练一个GAN model然后单独把GAN中的生成器模型抽取出来
废话不多说，直接开始上代码。本次开发基于keras
代码语言：javascript复制# example of training a gan on mnist
from numpy import expand_dims
from numpy import zeros
from numpy import ones
from numpy import vstack
from numpy.random import randn
from numpy.random import randint
from keras.datasets.mnist import load_data
from keras.optimizers import Adam
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Reshape
from keras.layers import Flatten
from keras.layers import Conv2D
from keras.layers import Conv2DTranspose
from keras.layers import LeakyReLU
from keras.layers import Dropout
from matplotlib import pyplot然后定义一个判别器模型，其实就是一个二分类的模型，作用就是判断输入的数据是fake or real
代码语言：javascript复制# define the standalone discriminator model
def define_discriminator(in_shape=(28,28,1)):
model = Sequential()
model.add(Conv2D(64, (3,3), strides=(2, 2), padding='same', input_shape=in_shape))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.4))
model.add(Conv2D(64, (3,3), strides=(2, 2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
model.add(Dropout(0.4))
model.add(Flatten())
model.add(Dense(1, activation='sigmoid'))
# compile model
opt = Adam(lr=0.0002, beta_1=0.5)
model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
return model然后是一个生成器模型，生成器主要负责接收一个随机输入，我们称之为来自于latent_space中的随机值或者是随机向量
代码语言：javascript复制# define the standalone generator model
def define_generator(latent_dim):
model = Sequential()
# foundation for 7x7 image
n_nodes = 128 * 7 * 7
model.add(Dense(n_nodes, input_dim=latent_dim))
model.add(LeakyReLU(alpha=0.2))
model.add(Reshape((7, 7, 128)))
# upsample to 14x14
model.add(Conv2DTranspose(128, (4,4), strides=(2,2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
# upsample to 28x28
model.add(Conv2DTranspose(128, (4,4), strides=(2,2), padding='same'))
model.add(LeakyReLU(alpha=0.2))
model.add(Conv2D(1, (7,7), activation='sigmoid', padding='same'))
return model然后是定义GAN模型，也就是接收G（生成器模型）和D（判别器模型）
代码语言：javascript复制# define the combined generator and discriminator model, for updating the generator
def define_gan(g_model, d_model):
# make weights in the discriminator not trainable
d_model.trainable = False
# connect them
model = Sequential()
# add generator
model.add(g_model)
# add the discriminator
model.add(d_model)
# compile model
opt = Adam(lr=0.0002, beta_1=0.5)
model.compile(loss='binary_crossentropy', optimizer=opt)
return model然后把数据做归一化处理
代码语言：javascript复制# load and prepare mnist training images
def load_real_samples():
# load mnist dataset
(trainX, _), (_, _) = load_data()
# expand to 3d, e.g. add channels dimension
X = expand_dims(trainX, axis=-1)
# convert from unsigned ints to floats
X = X.astype('float32')
# scale from [0,255] to [0,1]
X = X / 255.0
return X再写一个真实样本生成器，标签为1
代码语言：javascript复制# select real samples
def generate_real_samples(dataset, n_samples):
# choose random instances
ix = randint(0, dataset.shape[0], n_samples)
# retrieve selected images
X = dataset[ix]
# generate 'real' class labels (1)
y = ones((n_samples, 1))
return X, y再来一个假样本生成器，标签为0
代码语言：javascript复制# use the generator to generate n fake examples, with class labels
def generate_fake_samples(g_model, latent_dim, n_samples):
# generate points in latent space
x_input = generate_latent_points(latent_dim, n_samples)
# predict outputs
X = g_model.predict(x_input)
# create 'fake' class labels (0)
y = zeros((n_samples, 1))
return X, y再写一个生成随机值的函数，也就是来自于latent_spcae中的随机值
代码语言：javascript复制# generate points in latent space as input for the generator
def generate_latent_points(latent_dim, n_samples):
# generate points in the latent space
x_input = randn(latent_dim * n_samples)
# reshape into a batch of inputs for the network
x_input = x_input.reshape(n_samples, latent_dim)
return x_input在定义一个保存图片的函数
代码语言：javascript复制# create and save a plot of generated images (reversed grayscale)
def save_plot(examples, epoch, n=10):
# plot images
for i in range(n * n):
# define subplot
pyplot.subplot(n, n, 1 i)
# turn off axis
pyplot.axis('off')
# plot raw pixel data
pyplot.imshow(examples[i, :, :, 0], cmap='gray_r')
# save plot to file
filename = 'generated_plot_ed.png' % (epoch 1)
pyplot.savefig(filename)
pyplot.close()模型的评估函数：
代码语言：javascript复制# evaluate the discriminator, plot generated images, save generator model
def summarize_performance(epoch, g_model, d_model, dataset, latent_dim, n_samples=100):
# prepare real samples
X_real, y_real = generate_real_samples(dataset, n_samples)
# evaluate discriminator on real examples
_, acc_real = d_model.evaluate(X_real, y_real, verbose=0)
# prepare fake examples
x_fake, y_fake = generate_fake_samples(g_model, latent_dim, n_samples)
# evaluate discriminator on fake examples
_, acc_fake = d_model.evaluate(x_fake, y_fake, verbose=0)
# summarize discriminator performance
print('>Accuracy real: %.0f%%, fake: %.0f%%' % (acc_real*100, acc_fake*100))
# save plot
save_plot(x_fake, epoch)
# save the generator model tile file
filename = 'generator_model_d.h5' % (epoch 1)
g_model.save(filename)最后是训练函数：
代码语言：javascript复制# train the generator and discriminator
def train(g_model, d_model, gan_model, dataset, latent_dim, n_epochs=100, n_batch=256):
bat_per_epo = int(dataset.shape[0] / n_batch)
half_batch = int(n_batch / 2)
# manually enumerate epochs
for i in range(n_epochs):
# enumerate batches over the training set
for j in range(bat_per_epo):
# get randomly selected 'real' samples
X_real, y_real = generate_real_samples(dataset, half_batch)
# generate 'fake' examples
X_fake, y_fake = generate_fake_samples(g_model, latent_dim, half_batch)
# create training set for the discriminator
X, y = vstack((X_real, X_fake)), vstack((y_real, y_fake))
# update discriminator model weights
d_loss, _ = d_model.train_on_batch(X, y)
# prepare points in latent space as input for the generator
X_gan = generate_latent_points(latent_dim, n_batch)
# create inverted labels for the fake samples
y_gan = ones((n_batch, 1))
# update the generator via the discriminator's error
g_loss = gan_model.train_on_batch(X_gan, y_gan)
# summarize loss on this batch
print('>%d, %d/%d, d=%.3f, g=%.3f' % (i 1, j 1, bat_per_epo, d_loss, g_loss))
# evaluate the model performance, sometimes
if (i 1) % 10 == 0:
summarize_performance(i, g_model, d_model, dataset, latent_dim)
最后开始训练：
代码语言：javascript复制# size of the latent space
latent_dim = 100
# create the discriminator
d_model = define_discriminator()
# create the generator
g_model = define_generator(latent_dim)
# create the gan
gan_model = define_gan(g_model, d_model)
# load image data
dataset = load_real_samples()
# train model
train(g_model, d_model, gan_model, dataset, latent_dim)本机显卡太low，选择在云上跑的，跑了大概70个epoch我们的生成器模型生成的图片：
然后可以和第10epoch运行结束后生成的图形进行对比：
其实还是有很多的进步。
也就是说这些图像在现实生活中是不存在的，完全是由机器生成的。
