绕开bug的feed_dict，用自己的数据集训练DCGAN

这篇代码与上两篇博客紧密相连，在上篇博客的注意部分提到，feed_dict需要喂numpy.array这种数据，但是我自己用的方法生成队列batch的数据类型为tensor，那么就没法喂到feed_dict里面了，所以查了各种Stack Overflow后发现，绕开feed_dict的形式，去掉placeholder在图创建的时候，直接输入数据，就可以了。具体细节见下面代码。
为了博文的完整性，仍然本博客贴出完整代码。其共分成两部分：第一部分为generator和discriminator的model.py以及训练（无feeed_dict）的train.py两部分。有心的同学请仔细学习train.py文件，会发现跟之前博客（含有feed_dict）有所不同的。

• 顺便说一句，tf在训练的时候可以接受array和tensor这两种数据结构，之间会相互转化（猜测是由于自带的convolution之类的函数进行了转化）。因为仔细去看MNIST的数据集是array的形式。

model.py

# -*- coding: utf-8 -*-
"""
Created on Tue Jul 24 20:33:14 2018
E-mail: Eric2014_Lv@sjtu.edu.cn
@author: DidiLv
"""


import tensorflow as tf
import numpy as np


# import data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/") # MNIST dataset

# pooling and convolution definition
def conv2d(x, W):
    return tf.nn.conv2d(input = x, filter = W, strides = [1,1,1,1], padding = 'SAME')

def avg_pool_2x2(x):
    return tf.nn.avg_pool(x, ksize = [1,2,2,1], strides = [1,2,2,1], padding = 'SAME')

def xavier_init(size):
    in_dim = size[0]
    xavier_stddev = 1. / tf.sqrt(in_dim / 2.)
    return tf.random_normal(shape=size, stddev=xavier_stddev)
def sample_z(shape):
    return np.random.uniform(-1., 1., size=shape)

# discriminator
def discriminator(x_image, reuse=False):
    with tf.variable_scope('discriminator') as scope:
        if (reuse):
            tf.get_variable_scope().reuse_variables()
        #First Conv and Pool Layers
        W_conv1 = tf.get_variable('d_wconv1', shape = [5, 5, 1, 8], initializer=tf.truncated_normal_initializer(stddev=0.02))
        b_conv1 = tf.get_variable('d_bconv1', shape = [8], initializer=tf.constant_initializer(0))
        h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)        
        h_pool1 = avg_pool_2x2(h_conv1)

        #Second Conv and Pool Layers
        W_conv2 = tf.get_variable('d_wconv2', shape = [5, 5, 8, 16], initializer=tf.truncated_normal_initializer(stddev=0.02))
        b_conv2 = tf.get_variable('d_bconv2', shape = [16], initializer=tf.constant_initializer(0))
        h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
        h_pool2 = avg_pool_2x2(h_conv2)

        #First Fully Connected Layer
        W_fc1 = tf.get_variable('d_wfc1', [7 * 7 * 16, 32], initializer=tf.truncated_normal_initializer(stddev=0.02))
        b_fc1 = tf.get_variable('d_bfc1', [32], initializer=tf.constant_initializer(0))
        h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*16])
        h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

        #Second Fully Connected Layer
        W_fc2 = tf.get_variable('d_wfc2', [32, 1], initializer=tf.truncated_normal_initializer(stddev=0.02))
        b_fc2 = tf.get_variable('d_bfc2', [1], initializer=tf.constant_initializer(0))

        #Final Layer
        y_conv=(tf.matmul(h_fc1, W_fc2) + b_fc2)
    return y_conv


# generator from DCGAN, take a d-dimensional vector as input and upsample it to become a 28*28 image
# the structure is from https://arxiv.org/pdf/1511.06434v2.pdf
def generator(z, batch_size, z_dim, reuse = False):
    with tf.variable_scope('generator') as scope:
        if (reuse):
            tf.get_variable_scope().reuse_variables()
        ## number of filters for the first layer of generator 
        g_dim = 64
        ## color dimension of output 
        c_dim = 1
        ## size of output image
        s = 28
        s2, s4, s8, s16 = int(s/2), int(s/4), int(s/8), int(s/16)

        # h0 dimension is [batch_size, z_width, z_height, z_channel] 
        h0 = tf.reshape(z, [batch_size, s16+1, s16+1, 25])
        h0 = tf.nn.relu(h0)
        ##Dimensions of h0 = batch_size x 2 x 2 x 25

        # first decovolution layer (fractionally-strided convolution layer)

        ## useful link for convolution :
        ## https://blog.csdn.net/mao_xiao_feng/article/details/71713358
        output1_shape = [batch_size, s8, s8, g_dim*4]
        ## W_conv1 shape = [filter_height, filter_width, out_channels, in_channels]
        W_conv1 = tf.get_variable('g_wconv1', shape = [5,5,output1_shape[-1],int(h0.get_shape()[-1])],
                                    initializer=tf.truncated_normal_initializer(stddev = 0.1)
                                    )
        b_conv1 = tf.get_variable('g_bconv1', shape = [output1_shape[-1]], initializer=tf.constant_initializer(.1))
        ## H_conv1: h0 * W_conv1.T
        H_conv1 = tf.nn.conv2d_transpose(h0, W_conv1, output_shape = output1_shape, strides = [1,2,2,1], 
                                         padding = 'SAME')
        H_conv1 = tf.add(H_conv1, b_conv1)
        H_conv1 = tf.contrib.layers.batch_norm(inputs = H_conv1, center=True, scale=True, is_training=True, scope="g_bn1")
        H_conv1 = tf.nn.relu(H_conv1)
        ##Dimensions of H_conv1 = batch_size x 3 x 3 x 256

        # second deconvolution layer
        output2_shape = [batch_size, s4-1, s4-1, g_dim*2]
        W_conv2 = tf.get_variable('g_wconv2', shape = [5,5,output2_shape[-1], int(H_conv1.get_shape()[-1])],
                                  initializer=tf.truncated_normal_initializer(stddev = 0.1))
        b_conv2 = tf.get_variable('g_bconv2', shape = [output2_shape[-1]], initializer=tf.truncated_normal_initializer(0.1))
        H_conv2 = tf.nn.conv2d_transpose(H_conv1, W_conv2, output_shape = output2_shape, strides = [1,2,2,1],
                               padding = 'SAME')
        H_conv2 = tf.add(H_conv2, b_conv2)
        H_conv2 = tf.contrib.layers.batch_norm(inputs = H_conv2, center=True, scale=True, is_training=True, scope="g_bn2")    
        ##Dimensions of H_conv2 = batch_size x 6 x 6 x 128
        H_conv2 = tf.nn.relu(H_conv2)


        #third DeConv Layer
        output3_shape = [batch_size, s2 - 2, s2 - 2, g_dim*1]
        W_conv3 = tf.get_variable('g_wconv3', [5, 5, output3_shape[-1], int(H_conv2.get_shape()[-1])], 
                                  initializer=tf.truncated_normal_initializer(stddev=0.1))
        b_conv3 = tf.get_variable('g_bconv3', [output3_shape[-1]], initializer=tf.constant_initializer(.1))
        H_conv3 = tf.nn.conv2d_transpose(H_conv2, W_conv3, output_shape=output3_shape, strides=[1, 2, 2, 1], 
                                         padding='SAME')
        H_conv3 = tf.add(H_conv3, b_conv3)
        H_conv3 = tf.contrib.layers.batch_norm(inputs = H_conv3, center=True, scale=True, is_training=True, scope="g_bn3")
        H_conv3 = tf.nn.relu(H_conv3)
        #Dimensions of H_conv3 = batch_size x 12 x 12 x 64

        #Fourth DeConv Layer
        output4_shape = [batch_size, s, s, c_dim]
        W_conv4 = tf.get_variable('g_wconv4', [5, 5, output4_shape[-1], int(H_conv3.get_shape()[-1])], 
                                  initializer=tf.truncated_normal_initializer(stddev=0.1))
        b_conv4 = tf.get_variable('g_bconv4', [output4_shape[-1]], initializer=tf.constant_initializer(.1))
        H_conv4 = tf.nn.conv2d_transpose(H_conv3, W_conv4, output_shape=output4_shape, strides=[1, 2, 2, 1], 
                                         padding='VALID')
        H_conv4 = tf.add(H_conv4, b_conv4)
        H_conv4 = tf.nn.tanh(H_conv4)
        #Dimensions of H_conv4 = batch_size x 28 x 28 x 1
        return H_conv4

train.py

# -*- coding: utf-8 -*-
"""
Created on Wed Jul 25 09:42:35 2018
E-mail: Eric2014_Lv@sjtu.edu.cn
@author: DidiLv
"""
import model

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import random

# import data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/") # MNIST dataset


# reset the graph to reset all variables we test before
tf.reset_default_graph()

batch_size = 16
z_dimensions = 2*2*25 # details can be found in module of model: reshape of h0

##---------------------------------------------------------------------------------------------
## 去掉feed_dict，在图创建时应该做的更改
# discriminator for input
#x_placeholder = tf.placeholder(dtype = tf.float32, shape = [None, 28, 28, 1])
x_placeholder = np.reshape(mnist.train.next_batch(batch_size)[0], [batch_size, 28, 28, 1])

#z_placeholder = tf.placeholder(dtype = tf.float32, shape = [None,z_dimensions])
# 注意z随机做出来的是np.array的结构是float64,TF里面基本上都是float32所以要进行转换
z_placeholder = tf.Variable(np.random.normal(-1, 1, size=[batch_size, z_dimensions]), dtype = tf.float32)
##--------------------------------------------------------------------------------------------

Dx = model.discriminator(x_placeholder) # for real training data
Gz = model.generator(z_placeholder, batch_size, z_dimensions)
Dg = model.discriminator(Gz, reuse=True)


g_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Dg, labels=tf.ones_like(Dg)))
d_loss_real = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Dx, labels = tf.ones_like(Dx)))
d_loss_fake = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=Dg, labels = tf.zeros_like(Dx)))
d_loss = d_loss_real + d_loss_fake

tvars = tf.trainable_variables()
d_vars = [var for var in tvars if 'd_' in var.name]
g_vars = [var for var in tvars if 'g_' in var.name]

with tf.variable_scope(tf.get_variable_scope(), reuse = False):
    # var_list: tf.Variable to update to minimize loss
    trainerD = tf.train.AdadeltaOptimizer(learning_rate = 1e-3).minimize(d_loss, var_list = d_vars)
    trainerG = tf.train.AdadeltaOptimizer(learning_rate = 1e-3).minimize(g_loss, var_list = g_vars)



sess = tf.Session()
sess.run(tf.global_variables_initializer())
iterations = 3000
##----------------------------------------------------------------------------------------------------------------------------------------------
#for i in range(iterations):
#    z_batch = np.random.normal(-1, 1, size=[batch_size, z_dimensions])
#    real_image_batch = mnist.train.next_batch(batch_size)
#    real_image_batch = np.reshape(real_image_batch[0],[batch_size,28,28,1])
#    _,dLoss = sess.run([trainerD, d_loss],feed_dict={z_placeholder:z_batch,x_placeholder:real_image_batch}) #Update the discriminator
#    _,gLoss = sess.run([trainerG, g_loss],feed_dict={z_placeholder:z_batch}) #Update the generator
#    print((dLoss+gLoss))
##------------------------------------------------------------------------------------------------------------------------------------------------
## 去掉feed_dict的写法
for i in range(iterations):
    _,dLoss = sess.run([trainerD, d_loss]) #Update the discriminator
    _,gLoss = sess.run([trainerG, g_loss]) #Update the generator
    print((dLoss+gLoss))