LeNet-5手写字符识别

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/mabozi08/article/details/79280438

import tensorflow as tf

#定义神经网络结构相关的参数
INPUT_NODE=784
OUTPUT_NODE=10

IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10

CONV1_DEEP = 32
CONV1_SIZE = 5
CONV2_DEEP = 64
CONV2_SIZE = 5
FC_SIZE = 512
"""
def get_weight_variable(shape, regularizer):
    weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))

    if regularizer != None:
        tf.add_to_collection('losses',regularizer(weights))
    return weights
"""
#定义神经网络的前向传播
def inference(input_tensor, train, regularizer):
    #申明第一层神经网络的变量并完成前向传播过程，输入为28*28*1的原始图像，输出为28*28*32的矩阵
    with tf.variable_scope('layer1-conv1'):
        conv1_weights = tf.get_variable("weights", [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_DEEP],
                                        initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv1_biases = tf.get_variable("bias", [CONV1_DEEP], initializer=tf.constant_initializer(0.0))

        #使用边长为5，深度为32的过滤器，过滤器移动的步长为1， 且使用全0填充
        conv1 = tf.nn.conv2d(input_tensor, conv1_weights, strides=[1,1,1,1], padding='SAME')
        relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))

    #实现第二层池化层的前向传播过程，池化层过滤器的边长为2，使用全0填充，步长为2
    #输入为28*28*32的矩阵，输出为14*14*32的矩阵
    with tf.name_scope('layer2-pool1'):
        pool1 = tf.nn.max_pool(relu1, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

    #申明第三层神经网络的变量并完成前向传播过程。输入为14*14*32的矩阵，输出为14*14*64的矩阵
    with tf.variable_scope('layer3-conv2'):
        conv2_weights = tf.get_variable("weights", [CONV2_SIZE, CONV2_SIZE, CONV1_DEEP, CONV2_DEEP],
                                        initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv2_biases = tf.get_variable("bias", [CONV2_DEEP], initializer=tf.constant_initializer(0.0))

        #使用边长为5，深度为64的过滤器，过滤器移动的步长为1， 且使用全0填充
        conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1,1,1,1], padding='SAME')
        relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))

    #实现第四层池化层的前向传播过程。输入为14*14*64的矩阵，输出为7*7*64
    with tf.name_scope('layer4-pool2'):
        pool2 = tf.nn.max_pool(relu2, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')

    #将第四层池化层的输出转化为第五层全连接层的输入格式。将第四层的输出7*7*64的矩阵拉直成一个向量
    pool_shape = pool2.get_shape().as_list()  #得到第四层输出矩阵的维度
    #计算将矩阵拉直成向量之后的长度
    nodes = pool_shape[1] * pool_shape[2] * pool_shape[3]

    #将第四层的输出变成一个batch的向量
    reshaped = tf.reshape(pool2, [pool_shape[0], nodes])

    #申明第五层全连接层的变量并实现前向传播过程，输入是一组向量，长度为3136，输出长度512的向量
    with tf.variable_scope('layer5-fc1'):
        fc1_weights = tf.get_variable("weight", [nodes, FC_SIZE],
                                      initializer=tf.truncated_normal_initializer(stddev=0.1))
        #只有全连接的权重要正则化
        if regularizer !=None:
            tf.add_to_collection('losses', regularizer(fc1_weights))
        fc1_biases = tf.get_variable("bias", [FC_SIZE], initializer=tf.constant_initializer(0.1))

        fc1=tf.nn.relu(tf.matmul(reshaped, fc1_weights) + fc1_biases)
        if train: fc1 = tf.nn.dropout(fc1, 0.5)  #随机将部分节点的输出改为0，避免过拟合

    #申明第六层全连接层的变量并实现前向传播。输入为长度512的向量，输出为长度10的向量
    with tf.variable_scope('layer6-fc2'):
        fc2_weights = tf.get_variable("weights", [FC_SIZE, NUM_LABELS],
                                      initializer=tf.truncated_normal_initializer(stddev=0.1))
        if regularizer !=None:
            tf.add_to_collection('losses', regularizer(fc2_weights))
        fc2_biases = tf.get_variable("bias", [NUM_LABELS], initializer=tf.constant_initializer(0.1))
        logit = tf.matmul(fc1, fc2_weights) + fc2_biases

    return logit

import os
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#加载mnist_inference.py中定义的常量和前向传播的函数
import mnist_inference

#配置神经网络的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DEACY = 0.99
#模型保存的路径和文件名
MODEL_SAVE_PATH = r"E:\test\mnist\to-model"
MODEL_NAME = "model.ckpt"

def train(mnist):
    x = tf.placeholder(tf.float32, [
        BATCH_SIZE, 
        mnist_inference.IMAGE_SIZE, 
        mnist_inference.IMAGE_SIZE,
        mnist_inference.NUM_CHANNELS], 
        name='x-input')
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')

    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
    #直接使用mnist_inference.py中定义的前向传播过程
    y = mnist_inference.inference(x, train, regularizer)
    global_step = tf.Variable(0, trainable=False)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DEACY, global_step)
    variable_averages_op = variable_averages.apply(tf.trainable_variables())
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
    cross_entropy_mean = tf.reduce_mean(cross_entropy)
    loss = cross_entropy_mean + tf.add_n(tf.get_collection('losses'))
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variable_averages_op]):
        train_op = tf.no_op(name='train')
    if not os.path.exists(MODEL_SAVE_PATH):
        os.mkdir(MODEL_SAVE_PATH)
    #初始化tensorflow持久化类
    saver = tf.train.Saver()
    with tf.Session() as sess:
        # tf.initialize_all_variables().run()
        init = tf.global_variables_initializer()
        sess.run(init)
        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            reshaped_xs = np.reshape(xs, (BATCH_SIZE,
                                          mnist_inference.IMAGE_SIZE,
                                          mnist_inference.IMAGE_SIZE,
                                          mnist_inference.NUM_CHANNELS))
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: reshaped_xs, y_: ys})

            #每1000轮保存一次模型
            if  i % 1000 == 0:
                #输出当前训练的情况，输出模型在当前训练batch上的损失函数大小
                print("After %d training step(s), loss on training "
                "batch is %g." % (step, loss_value))
                #保存当前模型
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)

def main(argv=None):
    mnist = input_data.read_data_sets(r"E:\data\data_mnist", one_hot=True)
    train(mnist)

if __name__ == '__main__':
    tf.app.run()