tensorboard的使用

 # -*- coding: utf-8 -*-
 """
 Created on: 2017/10/29
 @author   : Shawn
 function  :
 """
 import tensorflow as tf
 from tensorflow.examples.tutorials.mnist import input_data

 # 入口函数
 if __name__ == '__main__':

     # 载入数据
     mnist = input_data.read_data_sets("MNIST_data", one_hot=True)

     # 每个批次的大小
     batch_size= 100

     # 计算一共有多少个批次
     n_batch= mnist.train.num_examples // batch_size

     # 命名空间
     with tf.name_scope('input'):
         # 定义两个placeholder
         x = tf.placeholder(tf.float32, [None, 784], name='x-input')  # 输入层784个神经元
         y = tf.placeholder(tf.float32, [None, 10], name='y-input')  # 输出层10个神经元，10类

     W = tf.Variable(tf.zeros([784, 10]))
     b = tf.Variable(tf.zeros([10]))
     prediction = tf.nn.softmax(tf.matmul(x, W)+b)

     # 二次代价函数
     # loss = tf.reduce_mean(tf.square(y-prediction))
     loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=prediction))

     # 使用梯度下降法
     # train_step= tf.train.GradientDescentOptimizer(0.2).minimize(loss) # 0.2为学习率
     train_step = tf.train.AdamOptimizer(1e-1).minimize(loss)

     # 初始化变量
     init = tf.global_variables_initializer()

     # 结果存在一个bool类型的列表中
     correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(prediction, 1)) # agmax返回一维张量中最大值所在的位置

     # 求准确率
     accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

     with tf.Session() as sess:
         sess.run(init)
         writer = tf.summary.FileWriter('logs/', sess.graph)

         # 把所有图片训练21次
         for epoch in range(1):

             # 训练n_batch批次
             for batch in range(n_batch):
                 batch_xs, batch_ys = mnist.train.next_batch(batch_size)
                 sess.run(train_step, feed_dict={x:batch_xs, y:batch_ys})

             acc = sess.run(accuracy, feed_dict={x:mnist.test.images, y:mnist.test.labels})
             print ("Iter " + str(epoch)+", Testing Accuracy" + str(acc))

     pass

代码

进入cmd:

tensorboard --logdir=F:\PycharmProjects\TFlearn\src\logs

输出一个网址：

用google浏览器或者火狐打开