【4-2】Tensorboard网络运行

一、参考代码

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

#载入数据集
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

#参数概要
def variable_summaries(var):                    #定义了一个函数，用来看平均值、标准差、最值
    mean = tf.reduce_mean(var)
    tf.summary.scalar('mean',mean)              #平均值
    with tf.name_scope('stddev'):
        stddev = tf.sqrt(tf.reduce_mean(tf.square(var - mean)))
    tf.summary.scalar('stddev',stddev)          #标准差
    tf.summary.scalar('max',tf.reduce_max(var)) #最大值
    tf.summary.scalar('min',tf.reduce_min(var)) #最小值
    tf.summary.histogram('histogram',var)       #直方图
 
#命名空间
with tf.name_scope('input'):
    #定义两个placeholder
    x = tf.placeholder(tf.float32,[None,784],name='x-input')
    y = tf.placeholder(tf.float32,[None,10],name='y-input')

    
with tf.name_scope('layer'):
    #创建一个简单的神经网络
    with tf.name_scope('wights'):
        W = tf.Variable(tf.zeros([784,10]),name='W')
        variable_summaries(W)           #将参数W传入创建的函数中
    with tf.name_scope('biases'):    
        b = tf.Variable(tf.zeros([10]),name='b')
        variable_summaries(b)           #将参数b传入创建的函数中
    with tf.name_scope('wx_plus_b'):
        wx_plus_b = tf.matmul(x,W) + b
    with tf.name_scope('softmax'):
        prediction = tf.nn.softmax(wx_plus_b)

#二次代价函数
# loss = tf.reduce_mean(tf.square(y-prediction))
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction))
    tf.summary.scalar('loss',loss)      #观察loss值的变化
with tf.name_scope('train'):
    #使用梯度下降法
    train_step = tf.train.GradientDescentOptimizer(0.2).minimize(loss)

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

with tf.name_scope('accuracy'):
    with tf.name_scope('correct_prediction'):
        #结果存放在一个布尔型列表中
        correct_prediction = tf.equal(tf.argmax(y,1),tf.argmax(prediction,1))#argmax返回一维张量中最大的值所在的位置
    with tf.name_scope('accuracy'):
        #求准确率
        accuracy = tf.reduce_mean(tf.cast(correct_prediction,tf.float32))
        tf.summary.scalar('accuracy',accuracy)  #观察准确率的变化
        
#合并所有的summary：我们要观测的参数
merged = tf.summary.merge_all()

with tf.Session() as sess:
    sess.run(init)
    writer = tf.summary.FileWriter('logs/',sess.graph)
    for epoch in range(51):
        for batch in range(n_batch):
            batch_xs,batch_ys =  mnist.train.next_batch(batch_size)
            summary,_ = sess.run([merged,train_step],feed_dict={x:batch_xs,y:batch_ys})  #执行train_step的同时，也执行merged
        
        writer.add_summary(summary,epoch)       #写入文件里
        
        acc = sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels})
        print("Iter " + str(epoch) + ",Testing Accuracy " + str(acc))

首先定义了一个函数variable_summaries()，用来看数据（比如W，b参数）的平均值，标准差，最值和直方图。

tf.summary.scalar('name',tensor)绘制变换的图表，第一项是字符命名，第二项是要记录跟踪的变量。

tf.summary.merge_all对所有训练图进行合并打包，最后必须用sess.run一下打包的图，writer.add_summary添加相应的记录。

二、Tensorboard中的结果：

还有显示一些参数的最值，分布等。但是因为只迭代了50次，所以图中点数为50。下面将点数改成2000，循环程序更改为：

    for i in range(2001):
        batch_xs,batch_ys = mnist.train.next_batch(batch_size)
        summary,_ = sess.run([merged,train_step],feed_dict={x:batch_xs,y:batch_ys})
        writer.add_summary(summary,i)
        if i%500 == 0:
            print(sess.run(accuracy,feed_dict={x:mnist.test.images,y:mnist.test.labels}))

有时会出现以下错误：

百度之后，说是因为当前路径不能有一个以上的events文件，所以将events文件删除，然后重新Restart&Run all之后，问题果真解决了。

参考：https://www.cnblogs.com/fydeblog/p/7429344.html 中例三：线性拟合

import tensorflow as tf
import numpy as np

#继续改进，试试其他功能：scalars，histograms，distributions
with tf.name_scope('data'):
    #原始数据
    x_data = np.random.rand(100).astype(np.float32)
    y_data = 0.3*x_data + 0.1

with tf.name_scope('parameters'):
    with tf.name_scope('weight'):
        weight = tf.Variable(tf.random_uniform([1],-1.0,1.0))
        tf.summary.histogram('weight',weight)                    #histogram
    with tf.name_scope('biases'):
        bias = tf.Variable(tf.zeros([1]))
        tf.summary.histogram('bias',bias)
    
with tf.name_scope('y_prediction'):
    y_prediction = weight*x_data + bias
    
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.square(y_data-y_prediction))
    tf.summary.scalar('loss',loss)
    
optimizer = tf.train.GradientDescentOptimizer(0.5)

with tf.name_scope('train'):
    train = optimizer.minimize(loss)
    
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    merged = tf.summary.merge_all()
    writer = tf.summary.FileWriter('logs/',sess.graph)
    for step in range(101):
        sess.run(train)
        rs = sess.run(merged)
        writer.add_summary(rs,step)

 2019-06-05 21:35:28