mnist detection example (使用CNN practice)*未解决问题

出现了bug，不知道怎么调试

运行结果一直是空的。

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
from tensorflow import float32

#载入数据
mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

#每个批次大小以及多少批次
batch_size = 100
n_batch = mnist.train.num_examples // batch_size

#初始化权值
def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)#生成一个正态分布
    return tf.Variable(initial)

#初始化偏置
def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

#卷积层
def conv2d(x, W):
    #strides=[1,1,1,1]第0 个和第三个都要设置为1？
    return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
    #ksize=（1,2,2,1）第0 个和第三个都要设置为1
    return tf.nn.max_pool(x, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')



#设置两个占位符
x = tf.placeholder(tf.float32, [None, 784])
y = tf.placeholder(tf.float32, [None, 10])

#改变x的格式转为4d的向量[batch,in_height, in_width, in_channels]
x_image = tf.reshape(x, [-1,28,28,1])

#初始化第一个卷积层的权值和偏置
W_conv1 = weight_variable([5,5,1,32])#采用5x5的采样窗口，32个卷积核从一个平面抽取特征
b_conv1 = bias_variable([32])#每个卷积核一个偏置值

#把x_image和权值向量进行卷积，在加上偏置值，然后应用于relu的激活函数
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)  #进行max_pooling

#初始化第二哥卷积层的权值和偏置
W_conv2 = weight_variable([5,5,32,64])#采用5x5的采样窗口，64个卷积核从32个平面抽取特征
b_conv2 = bias_variable([64])

#把第一个卷积层得到的结果和权值进行卷积，再加上偏置值，然后应用于relu的激活函数
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

#28*28的图片第一次卷积后还是28*28，第一次池化后变为14*14
#第二次卷积后为14*14，第二次池化后变成了7*7
#经过上面的操作后得到64张7*7的平面

#初始化第一个全连接层的权值
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])

#把池化层2的输出扁化为1维
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])

#求第一个全连接层的输出
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

#keep_prob用来表示神经元的输出概率
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1,keep_prob)

#初始化第二个全连接层
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

#计算输出
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)

#代价函数
cross_entropy = tf.reduce_mean(tf.square(y-prediction))                    
#使用AdamOptimizer下降方法
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

#结果放在布尔型列表中,其中argmax返回数列中最大值所在的位置
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(prediction,1))
#求准确性
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

#初始化变量
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    for epoch in range(2):
        for batch in range(n_batch):
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            sess.run(train_step, feed_dict={x:batch_xs, y:batch_ys, keep_prob:0.7})


        acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels, keep_prob:1})
        print("Iter " + str(epoch) + "Testing Accuracy= " + str(acc))
复制代码

转载于:https://juejin.im/post/5aa211dc5188250f7a19d82d