基于tensorflow的手写数字识别

柔情只为你懂 2022-11-21 04:30 265阅读 0赞

import numpy as np
    #import tensorflow as tf
    import tensorflow.compat.v1 as tf
    tf.disable_v2_behavior()         #解决tf.placeholder报错问题
    import matplotlib.pyplot as plt
    import input_data    #使用的数据库是tensorflow内置数据库，可下载到本地
    
    mnist = input_data.read_data_sets('data/',one_hot=True)
    
    #network topologies  网络拓扑
    n_hidden_1 = 256
    n_hidden_2 = 128
    n_input = 784
    n_classes = 10
    
    #inputs and outputs   输入 输出
    x = tf.placeholder("float",[None,n_input])
    y = tf.placeholder("float",[None,n_classes])
    
    #network parameters   网络参数
    stddev = 0.1
    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))
    }
    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 READY")
    
    def multilayer_perceptron(_X,_weights,_biases):
        layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(_X,_weights['w1']),_biases['b1']))
        layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1,_weights['w2']),_biases['b2']))
        return (tf.matmul(layer_2,_weights['out'])+_biases['out'])
    
    #prediction
    pred = multilayer_perceptron(x,weights,biases)
    #loss and optimizer  损失函数及优化器
    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"))
    #initializer
    init = tf.global_variables_initializer()
    print("FUNCTIONS READY")
    #迭代
    training_epochs = 20
    batch_size = 100
    display_step = 4
    
    #launch the graph
    sess = tf.Session()
    sess.run(init)
    
    #optimize
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size)
        #iteration
        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
        #display
        if (epoch+1)%display_step==0:
            print("Epoch:%03d/%03d cost:%.9f"%(epoch,training_epochs,avg_cost))
            feeds = {
        x:batch_xs,y:batch_ys}
            training_acc = sess.run(accr,feed_dict=feeds)
            print("Train Accuracy:%.3f"%(training_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")