深入浅出解读卷积神经网络

='Y')

return X,Y

X,Y=create_placeholder(64,3,6)

print("X="+str(X))

print("Y="+str(Y))

def weight_variable(shape):

return tf.Variable(tf.truncated_normal(shape,stddev=0.1))

def bias_variable(shape):

return tf.Variable(tf.constant(0.1,shape=shape))

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')

def initialize_parameters():

w_conv1=weight_variable([5,5,3,32])

b_conv1=bias_variable([32])

w_conv2=weight_variable([5,5,32,64])

b_conv2=bias_variable([64])

w_fc1=weight_variable([16*16*64,512])

b_fc1=bias_variable([512])

w_fc2=weight_variable([512,6])

b_fc2=bias_variable([6])

parameters={

"w_conv1":w_conv1,

"b_conv1":b_conv1,

"w_conv2":w_conv2,

"b_conv2":b_conv2,

"w_fc1":w_fc1,

"b_fc1":b_fc1,

"w_fc2":w_fc2,

"b_fc2":b_fc2

}

return parameters

第四步：前行传播过程

def forward_propagation(X,parameters): 
    w_conv1=parameters["w_conv1"] 
    b_conv1=parameters["b_conv1"] 
    h_conv1=tf.nn.relu(conv2d(X,w_conv1)+b_conv1) 
    h_pool1=max_pool_2x2(h_conv1) 
     
    w_conv2=parameters["w_conv2"] 
    b_conv2=parameters["b_conv2"	
			 3/5   首页 上一页 1 2 3 4 5 下一页 尾页	
			

　　推荐阅读
　　区块链分叉是怎么回事儿？终于懂了
            Tech Neo技巧沙龙 | 11月25号，九州云/ZStack与您一路商量云时代收集界线治理实践
            
                
                    
                
                最终，只有一条链会被保存下>>>详细阅读


本文标题：深入浅出解读卷积神经网络
地址：http://www.17bianji.com/lsqh/39218.html
 1/2    1