Python 使用GAN生成mnist，但不进行任何研究

最近，我在研究GAN网络，我用它来生成一个mnisit图像，我的计算机环境是ubuntu16.04，tensorflow，python3

代码可以正常运行，但结果表明网络没有学习任何东西，通过训练，输出的图像仍然是有噪声的图像

首先设计了一个生成网络：输入784维的噪声数据，通过一个隐藏层对其进行规则化，生成784维的图像

然后设计了一个鉴别器网络：输入是真图像和假图像，通过一个隐藏层对其进行规则化，输出是一维的logits

然后定义了发生器损耗和鉴别器损耗，然后对发生器和鉴别器进行训练，可以运行，但结果表明网络没有研究，损耗不能收敛

import tensorflow as tf
import numpy as np 
import tensorflow.contrib.slim as slim
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("/home/zyw/data/tensor_mnist-master/MNIST_data/",one_hot=True)
batch_size = 100

G_in = tf.placeholder(tf.float32,[None,784])
G_h1 = tf.layers.dense(G_in, 128)
G_h1 = tf.maximum(0.01 * G_h1, G_h1)
G_out = tf.tanh(tf.layers.dense(G_h1, 784)) 

real = tf.placeholder(tf.float32,[None,784]) 
Dl0 = tf.layers.dense(G_out, 128)
Dl0 = tf.maximum(0.01 * Dl0, Dl0)
p0 = tf.layers.dense(Dl0, 1)

Dl1 = tf.layers.dense(real, 128)
Dl1 = tf.maximum(0.01 * Dl1, Dl1)
p1 = tf.layers.dense(Dl1, 1)

G_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits =p0,labels=tf.ones_like(p0)*0.9))
D_real_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits =p1,labels=tf.ones_like(p1)*0.9))
D_fake_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits =p0,labels=tf.zeros_like(p0)))
D_total_loss = tf.add(D_fake_loss,D_real_loss) 

G_train = tf.train.AdamOptimizer(0.01).minimize(G_loss)
D_train = tf.train.AdamOptimizer(0.01).minimize(D_total_loss)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for i in range(1000):
        mnist_data,_ = mnist.train.next_batch(batch_size)

        # noise_org = tf.random_normal([batch_size,784],stddev = 0.1,dtype = tf.float32)
        noise_org = np.random.randn(batch_size, 784)
        a,b,dloss=  sess.run([D_real_loss,D_fake_loss,D_total_loss,G_train,D_train],feed_dict={G_in:noise_org,real:mnist_data})[:3]
        if i%100==0:
            print(a,b,dloss)
    #test_generative_image
    noise_org = np.random.randn(1, 784)
    image = sess.run(G_out,feed_dict ={G_in:noise_org})
    outimage = tf.reshape(image, [28,28])
    plt.imshow(outimage.eval(),cmap='gray')
    plt.show()
    print('ok')

结果是：

0.80509 0.63548 1.44057
0.33512 0.20223 0.53735
0.332536 0.97737 1.30991
0.328048 0.814452 1.1425
0.326688 0.411907 0.738596
0.325864 0.570807 0.896671
0.325575 0.970406 1.29598
0.325421 1.02487 1.35029
0.325222 1.34089 1.66612
0.325217 0.747129 1.07235

---

我已经添加了修改后的代码，并在其中添加了注释。此外，我在下面描述了我的变化

import tensorflow as tf
import numpy as np
import tensorflow.contrib.slim as slim
import matplotlib.pyplot as plt
from tensorflow.examples.tutorials.mnist import input_data

mnist = input_data.read_data_sets("/home/zyw/data/tensor_mnist-master/MNIST_data/",one_hot=True)

batch_size = 100

#define the generator function
def generator(input):
    G_h1 = tf.layers.dense(input, 128)
    # G_h1 = tf.maximum(0.01 * G_h1, G_h1)
    G_out = tf.sigmoid(tf.layers.dense(G_h1, 784))  # sigmoid function added
    return G_out

#Define the discrminator function
def discriminator(input):
    Dl0 = tf.layers.dense(input, 128)
    # Dl0 = tf.maximum(0.01 * Dl0, Dl0)
    p0 = tf.layers.dense(Dl0, 1)
    return p0

#Generator
with tf.variable_scope('G'):
    G_in = tf.placeholder(tf.float32, [None, 784])
    G_out = generator(G_in)

real = tf.placeholder(tf.float32, [None, 784])

#Discrimnator that takes the real data
with tf.variable_scope('D'):
    D1 = discriminator(real)

#Discriminator that takes fake data
with tf.variable_scope('D', reuse=True):  # need to use the same copy of Discrminator
    D2 = discriminator(G_out)

G_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=D2, labels=tf.ones_like(D2)))
D_real_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=D1, labels=tf.ones_like(D1)))
D_fake_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=D2, labels=tf.zeros_like(D2)))
D_total_loss = tf.add(D_fake_loss, D_real_loss)

vars = tf.trainable_variables() #all trainable variables
d_training_vars = [v for v in vars if v.name.startswith('D/')]  # varibles associated with the discrminator
g_training_vars = [v for v in vars if v.name.startswith('G/')]  # varibles associated with the generator

G_train = tf.train.AdamOptimizer(0.001).minimize(G_loss,var_list=g_training_vars)  # only train the variables associated with the generator
D_train = tf.train.AdamOptimizer(0.001).minimize(D_total_loss,var_list=d_training_vars)  # only train the variables associated with the discriminator

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    for i in range(1000):
        mnist_data, _ = mnist.train.next_batch(batch_size)
        # noise_org = tf.random_normal([batch_size,784],stddev = 0.1,dtype = tf.float32)
        noise_org = np.random.randn(batch_size, 784)

        a, b, dloss = sess.run([D_real_loss, D_fake_loss, D_total_loss, G_train, D_train],feed_dict={G_in: noise_org, real: mnist_data})[:3]
        if i % 100 == 0:
            print(a, b, dloss)

    # test_generative_image
    noise_org = np.random.randn(1, 784)
    image = sess.run(G_out, feed_dict={G_in: noise_org})
    outimage = tf.reshape(image, [28, 28])

    plt.imshow(outimage.eval(), cmap='gray')
    plt.show()
    print('ok')

在实现GAN时应注意的几点

需要使用相同的鉴别器副本，即共享相同的 在您的案例中实施鉴别器损耗时的权重Dl0 和Dl1应共享相同的参数。 发电机激活功能应为S形而非tanh形 因为发电机的输出应仅在0之间变化 和1。因为它是一个图像 训练鉴别器时，应只训练与鉴别器关联的变量。同样，在培训生成器时，只应培训与生成器关联的变量

有时，重要的是要确保鉴别器是正确的 比发电机更强大，否则，它不会 具备足够的学习能力，能够准确区分 在生成的样本和真实样本之间

这些只是你应该注意的GANs的基本内容。然而，在开发GaN时，还有许多其他方面需要考虑。通过阅读以下两篇文章，您可以对GANs有一个很好的基本了解

---

希望这有帮助。

请把你的问题说得更清楚。因为它写得太难看了。你真的没有5秒钟的时间来添加空格或新行，或者，纠正句子之间的标点符号吗，天哪，这很痛苦这是我第一次使用stackoverflow提问，我的英语不好，谢谢你的提醒，我会改正的，谢谢！根据你的建议，我改变了我的网络，这4点对我很有用，再次感谢你的回答。我将阅读这两篇文章。