tensorflow（五）神经网络实现mnist分类

最新推荐文章于 2023-03-20 10:48:48 发布

瑆箫

最新推荐文章于 2023-03-20 10:48:48 发布

阅读量327

点赞数 1

文章标签：神经网络图片

本文链接：https://blog.csdn.net/mo3408/article/details/80221276

版权

liunx 专栏收录该内容

33 篇文章 3 订阅

订阅专栏

#引入包
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
#引入input_data文件
from tensorflow.examples.tutorials.mnist import input_data
#读取文件
mnist = input_data.read_data_sets('F:/mnist/data/',one_hot=True)

#定义第一个隐藏层和第二个隐藏层，输入层输出层
n_hidden_1 = 256
n_hidden_2 = 128
n_input = 784
n_classes = 10

#由于不知道输入图片个数，所以用placeholder
x = tf.placeholder("float",[None,n_input])
y = tf.placeholder("float",[None,n_classes])

stddev = 0.1

#定义权重
weights = {
        'w1':tf.Variable(tf.random_normal([n_input,n_hidden_1],stddev = stddev)),
        'w2':tf.Variable(tf.random_normal([n_hidden_1,n_hidden_2],stddev=stddev)),
        'out':tf.Variable(tf.random_normal([n_hidden_2,n_classes],stddev=stddev))        
        }

#定义偏置
biases = {
        'b1':tf.Variable(tf.random_normal([n_hidden_1])),
        'b2':tf.Variable(tf.random_normal([n_hidden_2])),
        'out':tf.Variable(tf.random_normal([n_classes])), 
        }
print("Network is Ready")


#前向传播
def multilayer_perceptrin(_X,_weights,_biases):
    layer1 = tf.nn.sigmoid(tf.add(tf.matmul(_X,_weights['w1']),_biases['b1']))
    layer2 = tf.nn.sigmoid(tf.add(tf.matmul(layer1,_weights['w2']),_biases['b2']))
    return (tf.matmul(layer2,_weights['out'])+_biases['out'])

#定义优化函数，精准度等
pred = multilayer_perceptrin(x,weights,biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = pred,labels=y))
optm = tf.train.GradientDescentOptimizer(learning_rate = 0.001).minimize(cost)
corr = tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
accr = tf.reduce_mean(tf.cast(corr,"float"))
print("Functions is ready")

#定义超参数
training_epochs = 80
batch_size = 200
display_step = 4

#会话开始
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

#优化
for epoch in range(training_epochs):
    avg_cost=0.
    total_batch = int(mnist.train.num_examples/batch_size)

    for i in range(total_batch):
        batch_xs,batch_ys = mnist.train.next_batch(batch_size)
        feeds = {x:batch_xs,y:batch_ys}
        sess.run(optm,feed_dict = feeds)
        avg_cost += sess.run(cost,feed_dict=feeds)
    avg_cost = avg_cost/total_batch

    if (epoch+1) % display_step ==0:
        print("Epoch:%03d/%03d cost:%.9f"%(epoch,training_epochs,avg_cost))
        feeds = {x:batch_xs,y:batch_ys}
        train_acc = sess.run(accr,feed_dict = feeds)
        print("Train accuracy:%.3f"%(train_acc))
        feeds = {x:mnist.test.images,y:mnist.test.labels}
        test_acc = sess.run(accr,feed_dict = feeds)
        print("Test accuracy:%.3f"%(test_acc))
        print("Optimization Finished")程序部分运行结果如下：

Train accuracy:0.605
Test accuracy:0.633
Epoch:071/080 cost:1.810029302
Train accuracy:0.600
Test accuracy:0.645
Epoch:075/080 cost:1.761531130
Train accuracy:0.690
Test accuracy:0.649
Epoch:079/080 cost:1.711757494
Train accuracy:0.640
Test accuracy:0.660
Optimization Finished