经典卷积神经网络（CNN）实现MNIST分类（基于LeNet-5模型）

在机器视觉，图像处理领域，卷积神经网络取得了巨大的成功。本文将参考教程，结合自己的理解，利用Tensor Flow实现LeNet5，学习和理解卷积神经网络，网络上教程较多，此文不做重点介绍。

LeNet5_infernece.py

import tensorflow as tf

#配置神经网络的参数
INPUT_NODE = 784
OUTPUT_NODE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10

#第一层卷积层的尺寸和深度
CONV1_DEEP = 32
CONV1_SIZE = 5
#第二层卷积层的尺寸和深度
CONV2_DEEP = 64
CONV2_SIZE = 5
#全连接层的节点个数
FC_SIZE = 512

#
def inference(input_tensor, train, regularizer):
    #声明第一层卷积层的变量并实现前向传播过程
    with tf.variable_scope('layer1-conv1'):
        conv1_weights = tf.get_variable(
            "weight", [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))
        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))

    #声明第二层池化层的变量并实现前向传播过程
    with tf.name_scope("layer2-pool1"):
        pool1 = tf.nn.max_pool(relu1, ksize = [1,2,2,1],strides=[1,2,2,1],padding="SAME")
    
    #声明第三层卷积层的变量并实现前向传播过程
    with tf.variable_scope("layer3-conv2"):
        conv2_weights = tf.get_variable(
            "weight", [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))
        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))

    #声明第四层池化层的变量并实现前向传播过程
    with tf.name_scope("layer4-pool2"):
        pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
        pool_shape = pool2.get_shape().as_list()
        nodes = pool_shape[1] * pool_shape[2] * pool_shape[3]
        reshaped = tf.reshape(pool2, [pool_shape[0], nodes])

    #声明第五层卷积层的变量并实现前向传播过程
    with tf.variable_scope('layer5-fc1'):
        fc1_weights = tf.get_variable("weight", [nodes, FC_SIZE],
                                      initializer=tf.truncated_normal_initializer(stddev=0.1))
        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)

    #声明第六层池化层的变量并实现前向传播过程
    with tf.variable_scope('layer6-fc2'):
        fc2_weights = tf.get_variable("weight", [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

LeNet5_train.py

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import LeNet5_infernece
import os
import numpy as np
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

#定义神经网络相关的参数
BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 6000
MOVING_AVERAGE_DECAY = 0.99

#定义训练过程
def train(mnist):
    # 定义输出为4维矩阵的placeholder
    x = tf.placeholder(tf.float32, [
            BATCH_SIZE,
            LeNet5_infernece.IMAGE_SIZE,
            LeNet5_infernece.IMAGE_SIZE,
            LeNet5_infernece.NUM_CHANNELS],
        name='x-input')
    y_ = tf.placeholder(tf.float32, [None, LeNet5_infernece.OUTPUT_NODE], name='y-input')
    
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = LeNet5_infernece.inference(x,False,regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 定义损失函数、学习率、滑动平均操作以及训练过程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_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,
        staircase=True)

    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
    with tf.control_dependencies([train_step, variables_averages_op]):
        train_op = tf.no_op(name='train')
        
    # 初始化TensorFlow持久化类。
    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)

            reshaped_xs = np.reshape(xs, (
                BATCH_SIZE,
                LeNet5_infernece.IMAGE_SIZE,
                LeNet5_infernece.IMAGE_SIZE,
                LeNet5_infernece.NUM_CHANNELS))
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: reshaped_xs, y_: ys})

            if i % 1000 == 0:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))
#主程序入口
def main(argv=None):
    mnist = input_data.read_data_sets("../../../datasets/MNIST_data", one_hot=True)
    train(mnist)

if __name__ == '__main__':
    main()