python人工智能tensorflow构建卷积神经网络CNN
时间：2022-07-06 10:17:01 | 栏目：Python代码 | 点击：次
学习神经网络已经有一段时间，从普通的BP神经网络到LSTM长短期记忆网络都有一定的了解，但是从未系统的把整个神经网络的结构记录下来，我相信这些小记录可以帮助我更加深刻的理解神经网络。
简介
卷积神经网络（Convolutional Neural Networks, CNN）是一类包含卷积计算且具有深度结构的前馈神经网络（Feedforward Neural Networks），是深度学习（deep learning）的代表算法之一。
其主要结构分为输入层、隐含层、输出层。
在tensorboard中，其结构如图所示：
对于卷积神经网络而言，其输入层、输出层与平常的卷积神经网络无异。
但其隐含层可以分为三个部分，分别是卷积层（对输入数据进行特征提取）、池化层（特征选择和信息过滤）、全连接层（等价于传统前馈神经网络中的隐含层）。
隐含层介绍
1、卷积层
卷积将输入图像放进一组卷积滤波器，每个滤波器激活图像中的某些特征。
假设一副黑白图像为5*5的大小，像这样：
利用如下卷积器进行卷积：
卷积结果为：
卷积过程可以提取特征，卷积神经网络是根据特征来完成分类的。
在tensorflow中，卷积层的重要函数是：
tf.nn.conv2d(input, filter, strides, padding, use_cudnn_on_gpu=None, name=None)
其中：
1、input是输入量，shape是[batch, height, width, channels]。；
2、filter是使用的卷积核；
3、strides是步长，其格式[1,step,step,1]，step指的是在图像卷积的每一维的步长；
4、padding：string类型的量，只能是"SAME","VALID"其中之一，SAME表示卷积前后图像面积不变。
2、池化层
池化层用于在卷积层进行特征提取后，输出的特征图会被传递至池化层进行特征选择和信息过滤。
常见的池化是最大池化，最大池化指的是取出这些被卷积后的数据的最大值，就是取出其最大特征。
假设其池化窗口为2X2，步长为2。
原图像为：
池化后为：
在tensorflow中，池化层的重要函数是：
tf.nn.max_pool(value, ksize, strides, padding, data_format, name)
1、value：池化层的输入，一般池化层接在卷积层后面，shape是[batch, height, width, channels]。
2、ksize：池化窗口的大小，取一个四维向量，一般是[1, in_height, in_width, 1]。
3、strides：和卷积类似，窗口在每一个维度上滑动的步长，也是[1, stride,stride, 1]。
4、padding：和卷积类似，可以取’VALID’ 或者’SAME’。
这是tensorboard中卷积层和池化层的连接结构：
3、全连接层
全连接层与普通神经网络的结构相同，如图所示：
具体实现代码
卷积层、池化层与全连接层实现代码
def conv2d(x,W,step,pad): #用于进行卷积，x为输入值，w为卷积核
return tf.nn.conv2d(x,W,strides = [1,step,step,1],padding = pad)
def max_pool_2X2(x,step,pad): #用于池化，x为输入值，step为步数
return tf.nn.max_pool(x,ksize = [1,2,2,1],strides= [1,step,step,1],padding = pad)
def weight_variable(shape): #用于获得W
initial = tf.truncated_normal(shape,stddev = 0.1) #从截断的正态分布中输出随机值
return tf.Variable(initial)
def bias_variable(shape): #获得bias
initial = tf.constant(0.1,shape=shape) #生成普通值
return tf.Variable(initial)
def add_layer(inputs,in_size,out_size,n_layer,activation_function = None,keep_prob = 1):
#用于添加全连接层
layer_name = 'layer_%s'%n_layer
with tf.name_scope(layer_name):
with tf.name_scope("Weights"):
Weights = tf.Variable(tf.truncated_normal([in_size,out_size],stddev = 0.1),name = "Weights")
tf.summary.histogram(layer_name+"/weights",Weights)
with tf.name_scope("biases"):
biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name = "biases")
tf.summary.histogram(layer_name+"/biases",biases)
with tf.name_scope("Wx_plus_b"):
Wx_plus_b = tf.matmul(inputs,Weights) + biases
tf.summary.histogram(layer_name+"/Wx_plus_b",Wx_plus_b)
if activation_function == None :
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
print(activation_function)
outputs = tf.nn.dropout(outputs,keep_prob)
tf.summary.histogram(layer_name+"/outputs",outputs)
return outputs
def add_cnn_layer(inputs, in_z_dim, out_z_dim, n_layer, conv_step = 1, pool_step = 2, padding = "SAME"):
#用于生成卷积层和池化层
layer_name = 'layer_%s'%n_layer
with tf.name_scope(layer_name):
with tf.name_scope("Weights"):
W_conv = weight_variable([5,5,in_z_dim,out_z_dim])
with tf.name_scope("biases"):
b_conv = bias_variable([out_z_dim])
with tf.name_scope("conv"):
#卷积层
h_conv = tf.nn.relu(conv2d(inputs, W_conv, conv_step, padding)+b_conv)
with tf.name_scope("pooling"):
#池化层
h_pool = max_pool_2X2(h_conv, pool_step, padding)
return h_pool
全部代码
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data",one_hot = "true")
def conv2d(x,W,step,pad):
return tf.nn.conv2d(x,W,strides = [1,step,step,1],padding = pad)
def max_pool_2X2(x,step,pad):
return tf.nn.max_pool(x,ksize = [1,2,2,1],strides= [1,step,step,1],padding = pad)
def weight_variable(shape):
initial = tf.truncated_normal(shape,stddev = 0.1) #从截断的正态分布中输出随机值
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.1,shape=shape) #生成普通值
return tf.Variable(initial)
def add_layer(inputs,in_size,out_size,n_layer,activation_function = None,keep_prob = 1):
layer_name = 'layer_%s'%n_layer
with tf.name_scope(layer_name):
with tf.name_scope("Weights"):
Weights = tf.Variable(tf.truncated_normal([in_size,out_size],stddev = 0.1),name = "Weights")
tf.summary.histogram(layer_name+"/weights",Weights)
with tf.name_scope("biases"):
biases = tf.Variable(tf.zeros([1,out_size]) + 0.1,name = "biases")
tf.summary.histogram(layer_name+"/biases",biases)
with tf.name_scope("Wx_plus_b"):
Wx_plus_b = tf.matmul(inputs,Weights) + biases
tf.summary.histogram(layer_name+"/Wx_plus_b",Wx_plus_b)
if activation_function == None :
outputs = Wx_plus_b
else:
outputs = activation_function(Wx_plus_b)
print(activation_function)
outputs = tf.nn.dropout(outputs,keep_prob)
tf.summary.histogram(layer_name+"/outputs",outputs)
return outputs
def add_cnn_layer(inputs, in_z_dim, out_z_dim, n_layer, conv_step = 1, pool_step = 2, padding = "SAME"):
layer_name = 'layer_%s'%n_layer
with tf.name_scope(layer_name):
with tf.name_scope("Weights"):
W_conv = weight_variable([5,5,in_z_dim,out_z_dim])
with tf.name_scope("biases"):
b_conv = bias_variable([out_z_dim])
with tf.name_scope("conv"):
h_conv = tf.nn.relu(conv2d(inputs, W_conv, conv_step, padding)+b_conv)
with tf.name_scope("pooling"):
h_pool = max_pool_2X2(h_conv, pool_step, padding)
return h_pool
def compute_accuracy(x_data,y_data):
global prediction
y_pre = sess.run(prediction,feed_dict={xs:x_data,keep_prob:1})
correct_prediction = tf.equal(tf.arg_max(y_data,1),tf.arg_max(y_pre,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
result = sess.run(accuracy,feed_dict = {xs:batch_xs,ys:batch_ys,keep_prob:1})
return result
keep_prob = tf.placeholder(tf.float32)
xs = tf.placeholder(tf.float32,[None,784])
ys = tf.placeholder(tf.float32,[None,10])
x_image = tf.reshape(xs,[-1,28,28,1])
h_pool1 = add_cnn_layer(x_image, in_z_dim = 1, out_z_dim = 32, n_layer = "cnn1",)
h_pool2 = add_cnn_layer(h_pool1, in_z_dim = 32, out_z_dim = 64, n_layer = "cnn2",)
h_pool2_flat = tf.reshape(h_pool2,[-1,7*7*64])
h_fc1_drop = add_layer(h_pool2_flat, 7*7*64, 1024, "layer1", activation_function = tf.nn.relu, keep_prob = keep_prob)
prediction = add_layer(h_fc1_drop, 1024, 10, "layer2", activation_function = tf.nn.softmax, keep_prob = 1)
with tf.name_scope("loss"):
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=ys,logits = prediction),name = 'loss')
tf.summary.scalar("loss",loss)
train = tf.train.AdamOptimizer(1e-4).minimize(loss)
init = tf.initialize_all_variables()
merged = tf.summary.merge_all()
with tf.Session() as sess:
sess.run(init)
write = tf.summary.FileWriter("logs/",sess.graph)
for i in range(5000):
batch_xs,batch_ys = mnist.train.next_batch(100)
sess.run(train,feed_dict = {xs:batch_xs,ys:batch_ys,keep_prob:0.5})
if i % 100 == 0:
print(compute_accuracy(mnist.test.images,mnist.test.labels))