上篇的全部代码
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)
class DataDistribution(object):
def __init__(self):
self.mu = 4 #均值
self.sigma = 0.5 #标准差(初始状态蓝色的线)
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 #随机的初始化分布(G网络的输入)
def sample(self, N):
return np.linspace(-self.range, self.range, N) + \
np.random.random(N) * 0.01
#定义linear， 用于进行卷积
def linear(input, output_dim, scope=None, stddev=1.0):
norm = tf.random_normal_initializer(stddev=stddev) #w参数随机的初始化
const = tf.constant_initializer(0.0) #b参数直接初始化为常量0
with tf.variable_scope(scope or 'linear'):
w = tf.get_variable('w', [input.get_shape()[1], output_dim], initializer=norm)#声明w的shape大小
b = tf.get_variable('b', [output_dim], initializer=const)
return tf.matmul(input, w) + b
#定义generator,用于生成数据，这里使用两层神经网络
def generator(input, h_dim):
h0 = tf.nn.softplus(linear(input, h_dim, 'g0'))
h1 = linear(h0, 1, 'g1')
return h1
#定义discriminator函数，D判别式用于判别结果,使用了4层神经网络
def discriminator(input, h_dim):#input就是需要判别的数据，真实?生成?h_dim * 2隐藏神经元个数'd0'指定命名域linear控制w参数和b参数初始化
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
#定义optimizer函数，用于优化参数，学习率不断衰减的学习策略
def optimizer(loss, var_list, initial_learning_rate):
# 学习率衰减系数
decay = 0.95 #每次衰减为原来的0.95
num_decay_steps = 150 #每迭代150次进行一次学习率衰减
batch = tf.Variable(0)
#进行学习率的衰减
learning_rate = tf.train.exponential_decay( #tf的学习率衰减的学习方式
initial_learning_rate,
batch,
num_decay_steps,
decay,
staircase=True
)
# 梯度下降求解器
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(
loss,
global_step=batch,
var_list=var_list
)
return optimizer
class GAN(object):
# 初始化变量
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 #神经网络非常简易，只有4个神经元
self.learning_rate = 0.03
self._create_model()
# 建立模型
def _create_model(self):
# 建立预判别模型
with tf.variable_scope('D_pre'):#在D_pre域当中构造D_pre网络，为了训练获得D网络初始化参数
self.pre_input = tf.placeholder(tf.float32, shape=(self.batch_size, 1))#pre_input.shape=[12,1]12是batch，1是1维的点
self.pre_labels = tf.placeholder(tf.float32, shape=(self.batch_size, 1))#pre_labels.shape=[12,1]
# 获得预测结果
D_pre = discriminator(self.pre_input, self.mlp_hidden_size)#初始化
# 预测值与真实之间的差异
self.pre_loss = tf.reduce_mean(tf.square(D_pre - self.pre_labels))
# 训练缩小预测值与真实值的差异
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.
# 建立生成模型
with tf.variable_scope('Gen'):
# 伪造数据的生成
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.
# 建立判别模型
with tf.variable_scope('Disc') as scope:
# 对真实值做预测， D1为真实值的概率
self.x = tf.placeholder(tf.float32, shape=(self.batch_size, 1))
self.D1 = discriminator(self.x, self.mlp_hidden_size)
# 变量重用
scope.reuse_variables()
# 对生成数据做预测， D2为预测到造假值的概率
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
self.loss_d = tf.reduce_mean(-tf.log(self.D1) - tf.log(1 - self.D2))
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')
# 获得训练以后的参数
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 #训练次数
for step in range(num_pretrain_steps): #先训练D_pre网络
d = (np.random.random(self.batch_size) - 0.5) * 10.0
# 生成随机值的标签
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))
})
# 获得D_pre参数
self.weightsD = session.run(self.d_pre_params)
# copy weights from pre-training over to new D network
# 将d_pre_params 参数拷贝给 d_params
for i, v in enumerate(self.d_params):
session.run(v.assign(self.weightsD[i]))#有了D_pre往D网络进行真正的初始化
# 进行两个对抗函数的参数训练
for step in range(self.num_steps):
# update discriminator
x = self.data.sample(self.batch_size)#真实数据，有均值、标准差
z = self.gen.sample(self.batch_size) #随机的高斯初始化
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))
})
# 迭代一百次或者在最后一次进行画图
if step % self.log_every == 0:
print('{}: {}\t{}'.format(step, loss_d, loss_g))
if step % 100 == 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.title('1D Generative Adversarial Network')
plt.xlabel('Data values')
plt.ylabel('Probability density')
plt.legend()
plt.show()
def main(args):
# 初始化GAN实例
model = GAN(
# 产生真实值
DataDistribution(),
# 产生生成值
GeneratorDistribution(range=8),
args.num_steps, #一共迭代1200次
args.batch_size, #一次迭代12个点的数据
args.log_every, #隔多少次打印一次当前loss
)
model.train()
# 设置命令行选项
def parse_args():
parser = argparse.ArgumentParser()
# 用于参数的直接输入，默认值用default 表示
parser.add_argument('--num-steps', type=int, default=1200,
help='the number of training steps to take')
parser.add_argument('--batch-size', type=int, default=12,
help='the batch size')
parser.add_argument('--log-every', type=int, default=10,
help='print loss after this many steps')
return parser.parse_args()
if __name__ == '__main__':
main(parse_args())
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
