查看: 149|回复: 0

Tensorflow机器学习入门——MINIST数据集识别(卷积神经网络)

[复制链接]
发表于 2020-2-16 07:54:48 | 显示全部楼层 |阅读模式
  1. #自动下载并加载数据from tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets("MNIST_data/", one_hot=True)import tensorflow as tf# truncated_normal: https://www.cnblogs.com/superxuezhazha/p/9522036.htmldef 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)  #conv2d: https://blog.csdn.net/QQ_30934313/article/details/86626050   def conv2d(x, W):  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')#max_pool: https://blog.csdn.net/coder_xiaohui/article/details/78025379def max_pool_2x2(x):  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],strides=[1, 2, 2, 1], padding='SAME')x = tf.placeholder("float", shape=[None, 784])y_ = tf.placeholder("float", shape=[None, 10])keep_prob = tf.placeholder("float")#卷积池化1W_conv1 = weight_variable([5, 5, 1, 32])b_conv1 = bias_variable([32])x_image = tf.reshape(x, [-1,28,28,1])h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)h_pool1 = max_pool_2x2(h_conv1) #卷积池化2W_conv2 = weight_variable([5, 5, 32, 64])b_conv2 = bias_variable([64])h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)h_pool2 = max_pool_2x2(h_conv2)#全连接层1W_fc1 = weight_variable([7 * 7 * 64, 1024])b_fc1 = bias_variable([1024])h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)#dropout:https://blog.csdn.net/yangfengling1023/article/details/82911306h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)#全连接层2W_fc2 = weight_variable([1024, 10])b_fc2 = bias_variable([10])y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)#误差优化cross_entropy = -tf.reduce_sum(y_*tf.log(y_conv))train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)#计算准确率correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))#练习with tf.Session() as sess:    init = tf.initialize_all_variables()    sess.run(init)    for i in range(20000):        batch = mnist.train.next_batch(50)        if i%100 == 0:            train_accuracy = accuracy.eval(feed_dict={x:batch[0], y_: batch[1], keep_prob: 1.0})            print ("step %d, training accuracy %g"%(i, train_accuracy))        train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})    print ("test accuracy %g"%accuracy.eval(feed_dict={ x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))                           
复制代码

相关技术服务需求,请联系管理员和客服QQ:2753533861或QQ:619920289
您需要登录后才可以回帖 登录 | 用户注册

本版积分规则

帖子推荐:
客服咨询

QQ:2753533861

服务时间 9:00-22:00

快速回复 返回顶部 返回列表