经典卷积神经网络LeNet-5模型

经典的卷积神经网络模型有1998年的LeNet-5模型，2012年的AlexNet模型，2014年的VGG模型，2014年的GoogleNet模型和2015年的ResNet模型。
本文主要讲述经典LeNet-5模型，此模型一共有7层，结构如下图所示：

7层结构分别是：
卷积层-池化层-卷积层-池化层-全连接层-全连接层-全链接输出层
以下是LeNet-5模型的代码，在神经网络代码之上做的修改即可实现，代码如下。。。

此部分为LeNet-5模型中的lenet_inference.py代码部分，把神经网络的结构给改了，加入了卷积层和池化层。

# -*- coding: utf-8 -*-
"""
Created on Mon Jul 10 11:36:35 2017

@author: cxl
"""

import tensorflow as tf
#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 inference(input_tensor,train,regularizer):
    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))

        with tf.name_scope('layer2-pool1'):
            pool1 = tf.nn.max_pool(relu1,ksize = [1,2,2,1],strides=[1,2,2,1],
                padding = 'SAME')


    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))

        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])

    with tf.variable_scope('layer5-fc1'):
        fc1_weights = tf.get_variable("weights",[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)


    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

此部分为LeNet-5模型中的lenet_train.py代码部分,只修改了数据输入的格式。

# -*- coding: utf-8 -*-
"""
Created on Mon Jul 10 15:45:22 2017

@author: cxl
"""

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

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY=0.99
REGULARAZTION_RATE=0.0001
TRAINING_STEPS = 30000
MOVING_AVERAGE_DECAY=0.99

MODEL_SAVE_PATH = "./path/to/model/"
MODEL_NAME = "model.ckpt"

def train(mnist):
    x=tf.placeholder(tf.float32,[BATCH_SIZE,lenet_inference.IMAGE_SIZE,
        mnist_inference.IMAGE_SIZE,lenet_inference.NUM_CHANNELS],name='x-input')

    y_=tf.placeholder(tf.float32,[None,lenet_inference.NUM_LABELS],name='y-input')

    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)
    y = lenet_inference.inference(x,True,regularizer)
    global_step = tf.Variable(0,trainable=False)

    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)
    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')


    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.initialize_all_variables().run()
        for i in range(TRAINING_STEPS):
            xs,ys = mnist.train.next_batch(BATCH_SIZE)
            reshaped_xs = np.reshape(xs,(BATCH_SIZE,
                                         lenet_inference.IMAGE_SIZE,
                                         lenet_inference.IMAGE_SIZE,
                                         lenet_inference.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))
                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("/tmp/data",one_hot=True)    
    train(mnist)


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

此部分为LeNet-5模型中的lenet_eval.py代码部分，此部分也只修改了数据输入的格式。

# -*- coding: utf-8 -*-
"""
Created on Mon Jul 10 23:29:34 2017

@author: cxl
"""

import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
import lenet_inference
import lenet_train

EVAL_INTERVAL_SECS = 10

def evaluate(mnist):
    #with tf.Graph().as_default() as g:
    #x=tf.placeholder(tf.float32,[None,lenet_inference.INPUT_NODE],name = 'x-input')
    x=tf.placeholder(tf.float32,[mnist.validation.num_examples,
                                         lenet_inference.IMAGE_SIZE,
                                         lenet_inference.IMAGE_SIZE,
                                         lenet_inference.NUM_CHANNELS],name='x-input')
    y_= tf.placeholder(tf.float32,[None,lenet_inference.OUTPUT_NODE],name = 'y-input')

    xs,ys = mnist.validation.images,mnist.validation.labels
    reshaped_xs = np.reshape(xs,(mnist.validation.num_examples,
                                         lenet_inference.IMAGE_SIZE,
                                         lenet_inference.IMAGE_SIZE,
                                         lenet_inference.NUM_CHANNELS
                                         )) 

    validate_feed = {x:reshaped_xs,y_:ys}

    y = lenet_inference.inference(x,False,None)
    correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

    variable_averages = tf.train.ExponentialMovingAverage(
        lenet_train.MOVING_AVERAGE_DECAY)
    variables_to_restore = variable_averages.variables_to_restore()
    saver = tf.train.Saver(variables_to_restore)

    while True:
        with tf.Session() as sess:
            ckpt = tf.train.get_checkpoint_state(lenet_train.MODEL_SAVE_PATH)
            if ckpt and ckpt.model_checkpoint_path:
                saver.restore(sess,ckpt.model_checkpoint_path)
                global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1]
                accuracy_score = sess.run(accuracy,feed_dict = validate_feed)
                print("After %s training step(s),validation"
                      "accuracy = %g" % (global_step,accuracy_score))
            else:
                print("No checkpoint file found")
                return
                time.sleep(EVAL_INTERVAL_SECS)


def main(argv = None):
    mnist = input_data.read_data_sets("/tmp/data",one_hot = True)
    evaluate(mnist)


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

以上程序均已调试成功，如有错误，希望各位小伙伴加以批评指正哈！