分别是16个5*5的一通道的卷积核，以及16个偏移量。A2是转置一下，为了输出每一个卷积核，TensorFlow保存张量方法和人的理解有很大区别，A21 A31 A41 A51都是卷积核的权重矩阵偏移量
——————————————————————————————————————————————————————————————————————————————————————————————————
# -*- coding: utf-8 -*-
"""
Created on Fri Mar 9 10:16:39 2018
@author: DBSF
"""
import numpy as np
import matplotlib.pyplot as plt
import input_data
import tensorflow as tf
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
train_epochs = 2 # 训练轮数
batch_size = 100 # 随机出去数据大小
display_step = 1 # 显示训练结果的间隔
learning_rate= 0.0001 # 学习效率
drop_prob = 0.5 # 正则化,丢弃比例
fch_nodes = 512 # 全连接隐藏层神经元的个数
# 网络模型需要的一些辅助函数
# 权重初始化(卷积核初始化)
# tf.truncated_normal()不同于tf.random_normal(),返回的值中不会偏离均值两倍的标准差
# 参数shpae为一个列表对象,例如[5, 5, 1, 32]对应
# 5,5 表示卷积核的大小, 1代表通道channel,对彩色图片做卷积是3,单色灰度为1
# 最后一个数字32,卷积核的个数,(也就是卷基层提取的特征数量)
# 显式声明数据类型,切记
def weight_init(shape):
weights = tf.truncated_normal(shape, stddev=0.1,dtype=tf.float32)
return tf.Variable(weights)
# 偏置的初始化
def biases_init(shape):
biases = tf.random_normal(shape,dtype=tf.float32)
return tf.Variable(biases)
# 随机选取mini_batch
def get_random_batchdata(n_samples, batchsize):
start_index = np.random.randint(0, n_samples - batchsize)
return (start_index, start_index + batchsize)
def xavier_init(layer1, layer2, constant = 1):
Min = -constant * np.sqrt(6.0 / (layer1 + layer2))
Max = constant * np.sqrt(6.0 / (layer1 + layer2))
return tf.Variable(tf.random_uniform((layer1, layer2), minval = Min, maxval = Max, dtype = tf.float32))
def conv2d(x, w):
return tf.nn.conv2d(x, w, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])
# 把灰度图像一维向量,转换为28x28二维结构
x_image = tf.reshape(x, [-1, 28, 28, 1])
w_conv1 = weight_init([5, 5, 1, 16]) # 5x5,深度为1,16个
b_conv1 = biases_init([16])
h_conv1 = tf.nn.relu(conv2d(x_image, w_conv1) + b_conv1) # 输出张量的尺寸:28x28x16
h_pool1 = max_pool_2x2(h_conv1) # 池化后张量尺寸:14x14x16
# h_pool1 , 14x14的16个特征图
w_conv2 = weight_init([5, 5, 16, 32]) # 5x5,深度为16,32个
b_conv2 = biases_init([32])
h_conv2 = tf.nn.relu(conv2d(h_pool1, w_conv2) + b_conv2) # 输出张量的尺寸:14x14x32
h_pool2 = max_pool_2x2(h_conv2) # 池化后张量尺寸:7x7x32
# h_pool2 , 7x7的32个特征图
# h_pool2是一个7x7x32的tensor,将其转换为一个一维的向量
h_fpool2 = tf.reshape(h_pool2, [-1, 7*7*32])
# 全连接层,隐藏层节点为512个
# 权重初始化
w_fc1 = xavier_init(7*7*32, fch_nodes)
b_fc1 = biases_init([fch_nodes])
h_fc1 = tf.nn.relu(tf.matmul(h_fpool2, w_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob=drop_prob)
# 隐藏层与输出层权重初始化
w_fc2 = xavier_init(fch_nodes, 10)
b_fc2 = biases_init([10])
# 未激活的输出
y_ = tf.add(tf.matmul(h_fc1_drop, w_fc2), b_fc2)
# 激活后的输出
y_out = tf.nn.softmax(y_)
# 交叉熵代价函数
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y * tf.log(y_out), reduction_indices = [1]))
# tensorflow自带一个计算交叉熵的方法
# 输入没有进行非线性激活的输出值 和 对应真实标签
#cross_loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_, y))
# 优化器选择Adam(有多个选择)
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)
# 准确率
# 每个样本的预测结果是一个(1,10)的vector
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_out, 1))
# tf.cast把bool值转换为浮点数
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.global_variables_initializer()
mnist = input_data.read_data_sets('MNIST/mnist', one_hot=True)
n_samples = int(mnist.train.num_examples)
total_batches = int(n_samples / batch_size)
with tf.Session() as sess:
sess.run(init)
Cost = []
Accuracy = []
variable_names = [v.name for v in tf.trainable_variables()]
values = sess.run(variable_names)
for i in range(train_epochs):
for j in range(100):
start_index, end_index = get_random_batchdata(n_samples, batch_size)
batch_x = mnist.train.images[start_index: end_index]
batch_y = mnist.train.labels[start_index: end_index]
_, cost, accu = sess.run([ optimizer, cross_entropy,accuracy], feed_dict={x:batch_x, y:batch_y})
Cost.append(cost)
Accuracy.append(accu)
if i % display_step ==0:
print ('Epoch : %d , Cost : %.7f'%(i+1, cost))
A1=values[0]
A11=values[1]
A21=values[2]
A31=values[3]
A41=values[4]
A51=values[5]
A2=A1.transpose([3,2,1,0])
# with open('E:/TensorFlow/test00003.txt', 'w') as f:
# for z in range(16):
# for y in range(5):
# for x in range(5):
# f.write(str(A2[z][0][x][y]))
# f.write(',')
# f.write('****************\n')
# f.write('\n\n')