【DL笔记】LeNet5神经网络简介及TensorFlow实现

1.前言

这篇文章是我通过学习黄文坚、唐源所著的《TensorFlow实战》之后的简单总结，通过这本书我对深度学习更加了解，现整理出一部分分享给大家，错误之处可以在评论区指出，以便我加以改正，谢谢！

2.模型特点

LeNet5诞生于1994年，由Yann LeCun提出，充分考虑图像的相关性。当时结构的特点如下：

1）每个卷积层包含三个部分：卷积（Conv）、池化（ave-pooling）、非线性激活函数（sigmoid）

2）MLP作为最终的分类器

3）层与层之间稀疏连接减少计算复杂度

3.结构模型

4.网络层介绍

Input Layer：1*32*32图像

Conv1 Layer：包含6个卷积核，kernal size：5*5，parameters:（5*5+1）*6=156个

Subsampling Layer：average pooling，size：2*2

                                  Activation Function：sigmoid

Conv3 Layer：包含16个卷积核，kernal size：5*5  ->16个Feature Map

Subsampling Layer：average pooling，size：2*2

Conv5 Layer：包含120个卷积核，kernal size：5*5

Fully Connected Layer：Activation Function：sigmoid

Output Layer：Gaussian connection

5.代码实现

说明一下，原本应该放LeNet5的TensorFlow实现代码，发现LeNet5的模型在现在使用过程中好多地方进行了更改，比如激励函数换做ReLU，采用max pooling等等，因此，我只是简单地进行了一个CNN的TensorFlow代码实现，用的MNIST数据集，代码如下：

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

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])
x_image = tf.reshape(x,[-1,28,28,1])

# Conv1 Layer
W_conv1 = weight_variable([5,5,1,32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image,W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

# Conv2 Layer
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)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7*7*64,1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1) + b_fc1)

keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

W_fc2 = weight_variable([1024,10])
b_fc2 = bias_variable([10])
y_conv = tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2) + b_fc2)

cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y_conv),reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction = tf.equal(tf.argmax(y_conv,1),tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

tf.global_variables_initializer().run()
for i in range(20000):
	batch = mnist.train.next_batch(50)
	if i % 1000 == 0:
		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))
	train_step.run(feed_dict={x:batch[0],y_:batch[1],keep_prob:0.5})

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

在GPU上面训练，大概不到两分钟，准确率99.11%

注：系统环境：ubuntu、Python3.5.2、TensorFlow1.2.0