TensorFlow的MNIST手写数字数据包及图片还原小程序

# -*- coding:utf-8 -*- import tensorflow as tf import tensorflow.examples.tutorials.mnist.input_data as input_data import random #读取mnist数据，下载后的Mnist并解压后，放在项目的同级目录下，通过下面程序即可读取 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) def showImg(isTrain=True,index=None,zeroRate=0.8): ''' 参数说明： isTrain：是读取训练集，还是测试集 index：读第几张图，其中训练集共55000张，测试集共10000张，当为None时随机读取 zeroRate：当值小于0.8时显示为空，大于0.8时显示为1,当这个值越小时，整张图的字体显示越粗 ''' d=mnist.train.images if isTrain else mnist.test.images index= random.randint(0,len(d)-1) if index==None else 0 if index<0 else len(d)-1 if index>=len(d) else index item=["1" if x>=0.8 else " " for x in d[index]] for i in range(28):print(''.join(i for i in item[i*28:i*28+28])) showImg() def abc(): x = tf.placeholder("float", [None, 784]) W = tf.Variable(tf.zeros([784,10])) b = tf.Variable(tf.zeros([10])) y = tf.nn.softmax(tf.matmul(x,W) + b) y_ = tf.placeholder("float", [None,10]) cross_entropy = -tf.reduce_sum(y_*tf.log(y)) train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy) init = tf.initialize_all_variables() sess = tf.Session() sess.run(init) for i in range(1000): batch_xs, batch_ys = mnist.train.next_batch(100) sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys}) correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1)) accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) print( sess.run(accuracy, feed_dict={x: mnist.test.images, y_: mnist.test.labels})) sess.close()