【Tensorflow】Mnist初步实践

骑猪看日落 2022-05-11 02:46 206阅读 0赞

1. 首先[下载MNIST][MNIST] （这里采用离线下载再读取的方法。在线安装由于SSL权限的问题，可以参考

[http://www.tensorfly.cn/tfdoc/tutorials/mnist\_download.html][http_www.tensorfly.cn_tfdoc_tutorials_mnist_download.html] ）

2.读入MNIST

from tensorflow.examples.tutorials.mnist import input_data
    import tensorflow as tf
    
    MNIST_dir = 'C:\\Users\\HAPPY\\Desktop\\mnist'  #MNIST文件夹目录
    mnist = input_data.read_data_sets(MNIST_dir, one_hot=True)

3.训练代码（此处训练10000次，设置学习率为0.03，最后调出的识别准确率为89％左右）

# coding:utf-8
    from tensorflow.examples.tutorials.mnist import input_data
    import tensorflow as tf
    import numpy as np
    import os
    
    os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
    MNIST_dir = 'C:\\Users\\HAPPY\\Desktop\\mnist'
    
    mnist = input_data.read_data_sets(MNIST_dir, one_hot=True)
    
    x = tf.placeholder(tf.float32, shape=[None, 784])
    y_ = tf.placeholder(tf.float32, shape=[None, 10])
    
    w = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))
    
    y = tf.nn.softmax(tf.matmul(x, w) + b)
    
    loss = -tf.reduce_mean(y_ * tf.log(y))
    train_steps = tf.train.GradientDescentOptimizer(0.03).minimize(loss)
    
    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())
        for i in range(10000):
            batch_x, batch_y = mnist.train.next_batch(100)
            sess.run(train_steps, {x: batch_x, y_: batch_y})
            if i % 1000 == 0:
                print("now steps: %d" % int(i))
        correct_prediction = tf.equal(tf.arg_max(y, 1), tf.argmax(y_, 1)) #测试最后的准确率
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        print(sess.run(accuracy, {x: mnist.test.images, y_: mnist.test.labels}))

[MNIST]: http://yann.lecun.com/exdb/mnist/
[http_www.tensorfly.cn_tfdoc_tutorials_mnist_download.html]: http://www.tensorfly.cn/tfdoc/tutorials/mnist_download.html