Tensorflow機器學習入門——網路可視化TensorBoard

一、在代碼中標記要顯示的各種量

tensorboard各函數的作用和用法請參考：https://www.cnblogs.com/lyc-seu/p/8647792.html

import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import os
#設置當前工作目錄
os.chdir(r'H:\Notepad\Tensorflow')

def add_layer(inputs, in_size, out_size, n_layer, activation_function=None):
    layer_name = 'layer%s' % n_layer
    with tf.name_scope(layer_name):
    
        Weights = tf.Variable(tf.random_normal([in_size, out_size]), name='W')
        biases = tf.Variable(tf.zeros([1, out_size]) + 0.1, name='b')
        Wx_plus_b = tf.add(tf.matmul(inputs, Weights), biases)
        if activation_function is None:
            outputs = Wx_plus_b
        else:
            outputs = activation_function(Wx_plus_b, )
            
    #histogram用來顯示訓練過程中變數的分佈情況        
    tf.summary.histogram(layer_name + '/weights', Weights)
    tf.summary.histogram(layer_name + '/biases', biases)
    tf.summary.histogram(layer_name + '/outputs', outputs)
        
    return outputs
    
#數據   
x_data = np.linspace(-1,1,300)[:, np.newaxis]
noise = np.random.normal(0, 0.05, x_data.shape)
y_data = 5*np.square(x_data) - 0.5 + noise

#輸入
with tf.name_scope('inputs'):
    xs = tf.placeholder(tf.float32, [None, 1], name='x_input')
    ys = tf.placeholder(tf.float32, [None, 1], name='y_input')

#3層網路
l1 = add_layer(xs, 1, 10, 1,activation_function=tf.nn.relu)
l2 = add_layer(l1, 10, 10,2, activation_function=tf.nn.relu)
prediction = add_layer(l2, 10, 1,3, activation_function=None)

#損失與訓練
with tf.name_scope('loss'):
    loss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),
                                        reduction_indices=[1]))
    tf.summary.scalar('loss-haha', loss)
with tf.name_scope('train'):
    train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)

#運行    
init = tf.global_variables_initializer()
#merge_all 可以將所有summary全部保存到磁碟，以便tensorboard顯示。
merged = tf.summary.merge_all()
with tf.Session() as sess:
    sess.run(init)
　　#FileWriter指定一個文件用來保存圖。可以調用其add_summary（）方法將訓練過程數據保存在filewriter指定的文件中
    writer = tf.summary.FileWriter("logs/", sess.graph)#輸出Graph
    for i in range(10000):
        sess.run(train_step, feed_dict={xs: x_data, ys: y_data})
        if i % 50 == 0:
            result = sess.run(merged,feed_dict={xs: x_data, ys: y_data})
            writer.add_summary(result, i)    

二、在log文件夾所在目錄打開cmd，並輸入‘     tensorboard --logdir=logs     ’ 

 三、在Google Chrome瀏覽器中輸入cmd中給出的網址： http://Fengqiao_x:6006