TensorFlow实战Chp4--基于MNIST实现简单的卷积神经网络

• TensorFlow实战Chp4–基于MNIST实现简单的卷积神经网络

# -*- coding: utf-8 -*-
"""
Created on Sun Dec 30 19:36:15 2018

@author: muli
"""

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf


# 加载数据
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
sess = tf.InteractiveSession()

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

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])

# -1:代表样本的数量不固定
x_image = tf.reshape(x, [-1,28,28,1])

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
# 卷积并通过激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
# 池化层
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
# 此时tensor的尺寸为7*7*64
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
# 将第二卷积层的转换为 1D 向量
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
# 全连接层
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# 比率
keep_prob = tf.placeholder(tf.float32)
# Dropout层
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
# 将Dropout层 连接 Softmax层
y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

# 交叉熵损失
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv), reduction_indices=[1]))
# 反向传播
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
# 准确率
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# 全局变量初始化
tf.global_variables_initializer().run()

for i in range(3000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    # 训练精度
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
  # 反向传播
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})

# 测试精度
print("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))