# 【学习笔记】训练简单生成对抗网络

本实例训练一个简单的GAN，实现让噪声点分布逼近Ground Truth分布的功能，使用的是简单的一维数据点。初始数据分布如图：

GAN训练主要分为两步：

1、定义G网络和D网络，及其Loss，Loss在GAN的论文中有讲述,其中x为真实值，Z为生成值，即：

可以将其拆分为判别模型loss:

生成模型Loss:

2.训练G网络和D网络，使得Loss最小，这样G网络生成的数据能“骗过”D网络的检测，训练的过程就是G逐渐对抗D，逼近真实值的过程。

代码如下：

import argparse
import numpy as np
from scipy.stats import norm
import tensorflow as tf
import matplotlib.pyplot as plt
from matplotlib import animation
import seaborn as sns

sns.set(color_codes=True)

seed = 42
np.random.seed(seed)
tf.set_random_seed(seed)

def __init__(self):
self.mu = 4
self.sigma = 0.5

def sample(self, N):
samples = np.random.normal(self.mu, self.sigma, N)
samples.sort()
return samples

class GeneratorDistribution(object):
def __init__(self, range):
self.range = range

def sample(self, N):
return np.linspace(-self.range, self.range, N) + \
np.random.random(N) * 0.01

#w*x+b
def linear(input, output_dim, scope=None, stddev=1.0):
norm = tf.random_normal_initializer(stddev=stddev)
const = tf.constant_initializer(0.0)
with tf.variable_scope(scope or 'linear'):
w = tf.get_variable('w', [input.get_shape()[1], output_dim], initializer=norm)
b = tf.get_variable('b', [output_dim], initializer=const)
return tf.matmul(input, w) + b

def generator(input, h_dim):
#h0=log( exp(w*input+b) + 1)
h0 = tf.nn.softplus(linear(input, h_dim, 'g0'))
h1 = linear(h0, 1, 'g1')
return h1

#Simple 3-layers Nural Network,output a probability
def discriminator(input, h_dim):
h0 = tf.tanh(linear(input, h_dim * 2, 'd0'))
h1 = tf.tanh(linear(h0, h_dim * 2, 'd1'))
h2 = tf.tanh(linear(h1, h_dim * 2, scope='d2'))

h3 = tf.sigmoid(linear(h2, 1, scope='d3'))
return h3

def optimizer(loss, var_list, initial_learning_rate):
decay = 0.95
num_decay_steps = 150
batch = tf.Variable(0)
learning_rate = tf.train.exponential_decay(
initial_learning_rate,
batch,
num_decay_steps,
decay,
staircase=True
)
loss,
global_step=batch,
var_list=var_list
)
return optimizer

class GAN(object):
def __init__(self, data, gen, num_steps, batch_size, log_every):
self.data = data
self.gen = gen
self.num_steps = num_steps
self.batch_size = batch_size
self.log_every = log_every
self.mlp_hidden_size = 4

self.learning_rate = 0.03

self._create_model()

def _create_model(self):

with tf.variable_scope('D_pre'):
self.pre_input = tf.placeholder(tf.float32, shape=(self.batch_size, 1))
self.pre_labels = tf.placeholder(tf.float32, shape=(self.batch_size, 1))
D_pre = discriminator(self.pre_input, self.mlp_hidden_size)
self.pre_loss = tf.reduce_mean(tf.square(D_pre - self.pre_labels))
self.pre_opt = optimizer(self.pre_loss, None, self.learning_rate)

# This defines the generator network - it takes samples from a noise
# distribution as input, and passes them through an MLP.
with tf.variable_scope('Gen'):
#generate G(z) data from random noisy z data
self.z = tf.placeholder(tf.float32, shape=(self.batch_size, 1))
self.G = generator(self.z, self.mlp_hidden_size)

# The discriminator tries to tell the difference between samples from the
# true data distribution (self.x) and the generated samples (self.z).
#
# Here we create two copies of the discriminator network (that share parameters),
# as you cannot use the same network with different inputs in TensorFlow.
with tf.variable_scope('Disc') as scope:
self.x = tf.placeholder(tf.float32, shape=(self.batch_size, 1))
#self.D1 :True Data
self.D1 = discriminator(self.x, self.mlp_hidden_size)
#share variables between two network
scope.reuse_variables()
#self.D2: generator data
self.D2 = discriminator(self.G, self.mlp_hidden_size)

# Define the loss for discriminator and generator networks (see the original
# paper for details), and create optimizers for both
#discriminator network loss
self.loss_d = tf.reduce_mean(-tf.log(self.D1) - tf.log(1 - self.D2))
#generator network loss
self.loss_g = tf.reduce_mean(-tf.log(self.D2))

self.d_pre_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='D_pre')
self.d_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='Disc')
self.g_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope='Gen')

self.opt_d = optimizer(self.loss_d, self.d_params, self.learning_rate)
self.opt_g = optimizer(self.loss_g, self.g_params, self.learning_rate)

def train(self):
with tf.Session() as session:
tf.global_variables_initializer().run()

# pretraining discriminator
num_pretrain_steps = 1000
for step in range(num_pretrain_steps):
d = (np.random.random(self.batch_size) - 0.5) * 10.0
labels = norm.pdf(d, loc=self.data.mu, scale=self.data.sigma)
pretrain_loss, _ = session.run([self.pre_loss, self.pre_opt], {
self.pre_input: np.reshape(d, (self.batch_size, 1)),
self.pre_labels: np.reshape(labels, (self.batch_size, 1))
})
self.weightsD = session.run(self.d_pre_params)
# copy weights from pre-training over to new D network
for i, v in enumerate(self.d_params):
session.run(v.assign(self.weightsD[i]))

for step in range(self.num_steps):
# update discriminator
x = self.data.sample(self.batch_size)
z = self.gen.sample(self.batch_size)
loss_d, _ = session.run([self.loss_d, self.opt_d], {
self.x: np.reshape(x, (self.batch_size, 1)),
self.z: np.reshape(z, (self.batch_size, 1))
})

# update generator
z = self.gen.sample(self.batch_size)
loss_g, _ = session.run([self.loss_g, self.opt_g], {
self.z: np.reshape(z, (self.batch_size, 1))
})

if step % self.log_every == 0:
print('{}: {}\t{}'.format(step, loss_d, loss_g))
if step % 1000 == 0 or step==0 or step == self.num_steps -1 :
self._plot_distributions(session)

def _samples(self, session, num_points=10000, num_bins=100):
xs = np.linspace(-self.gen.range, self.gen.range, num_points)
bins = np.linspace(-self.gen.range, self.gen.range, num_bins)

# data distribution
d = self.data.sample(num_points)
pd, _ = np.histogram(d, bins=bins, density=True)

# generated samples
zs = np.linspace(-self.gen.range, self.gen.range, num_points)
g = np.zeros((num_points, 1))
for i in range(num_points // self.batch_size):
g[self.batch_size * i:self.batch_size * (i + 1)] = session.run(self.G, {
self.z: np.reshape(
zs[self.batch_size * i:self.batch_size * (i + 1)],
(self.batch_size, 1)
)
})
pg, _ = np.histogram(g, bins=bins, density=True)

return pd, pg

def _plot_distributions(self, session):
pd, pg = self._samples(session)
p_x = np.linspace(-self.gen.range, self.gen.range, len(pd))
f, ax = plt.subplots(1)
ax.set_ylim(0, 1)
plt.plot(p_x, pd, label='real data')
plt.plot(p_x, pg, label='generated data')
plt.xlabel('Data values')
plt.ylabel('Probability density')
plt.legend()
plt.show()
def main(args):
model = GAN(
GeneratorDistribution(range=8),
args.num_steps,
args.batch_size,
args.log_every,
)
model.train()

def parse_args():
parser = argparse.ArgumentParser()
help='the number of training steps to take')
help='the batch size')
help='print loss after this many steps')
return parser.parse_args()

if __name__ == '__main__':
main(parse_args())