tensorflow实现卷积神经网络手写数字识别

最新推荐文章于 2024-06-06 12:17:01 发布

原创最新推荐文章于 2024-06-06 12:17:01 发布 · 322 阅读

0 ·

CC 4.0 BY-SA版权

博客内容提及最终得到一个7*7的64通路的tensor，这可能涉及到数据处理或模型构建等信息技术相关操作。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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

mnist=input_data.read_data_sets('MNIST_data',one_hot=True)

batch_size=100#批次大小
n_batch=mnist.train.num_examples//batch_size#批次数量

#初始化权重
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)

#卷积层
def conv2d(x,W):
    #x是输入【batch,输入高度，输入宽度，输入通道】
    #W是过滤器【高度，宽度，输入通道数，输出通道数】
    #stride【0】=stride【3】，stride【1】代表x方向步长，stride【2】代表y方向的步长
    #padding：“SAME”，"VALID"
    return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME')

#池化层
def max_pool2_2(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])
#初始化第一层偏差与权重
W_conv1=weight_variable([5,5,1,32])
b_conv1=bias_variable([32])
#把x_image和权值进行卷积，再加上偏置，再用激活函数
h_conv1=tf.nn.relu(conv2d(x_image,W_conv1)+b_conv1)
h_pool1=max_pool2_2(h_conv1)

#第二层
#初始化
W_conv2=weight_variable([5,5,32,64])
b_conv2=bias_variable([64])
#卷积
h_conv2=tf.nn.relu(conv2d(h_pool1,W_conv2)+b_conv2)
h_pool2=max_pool2_2(h_conv2)

28*28图片第一次卷积以后是28*28，第一次池化后为14*14，
第二次卷积为14*14，池化后为7*7,

最后得到一个7*7的64通路的tensor

#初始化全连接层
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_fcl=tf.nn.relu(tf.matmul(h_pool2_flat,W_fc1)+b_fc1)

#keep_prob输出概率
keep_prob=tf.placeholder(tf.float32)
h_fc1_drop=tf.nn.dropout(h_fcl,keep_prob)
#第二个全连接层
W_fc2=weight_variable([1024,10])
b_fc2=bias_variable([10])
predction=tf.nn.softmax(tf.matmul(h_fc1_drop,W_fc2)+b_fc2)
cross_entropy=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=predction))
train_step=tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)

correct_prediction=tf.equal(tf.arg_max(predction,1),tf.arg_max(y,1))
accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32))

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    for epoch in range(21):
        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:1.0})
 
       print("Iter"+str(epoch)+" Testing Accuracy= "+str(acc))

运行结果如下：
Iter0 Testing Accuracy= 0.9472
Iter1 Testing Accuracy= 0.971
Iter2 Testing Accuracy= 0.9751
Iter3 Testing Accuracy= 0.9796
Iter4 Testing Accuracy= 0.9833
Iter5 Testing Accuracy= 0.985
Iter6 Testing Accuracy= 0.987
Iter7 Testing Accuracy= 0.9864
Iter8 Testing Accuracy= 0.9876
Iter9 Testing Accuracy= 0.9872
Iter10 Testing Accuracy= 0.9878