TensorBoard的运用

使用方式：

1、用TensorFlow保存图的信息到日志中

tf.summary.FileWriter("路径",sess.graph)

2、用TensorBoard读取并展示日志

tensorboard --logdir=路径

TensorBoard图标：

eg：tensorboard --logdir=/tmp/hello

(要注意的是，浏览器会使用6006端口)

import tensorflow as tf

#y = W * x + b
W = tf.Variable(2.0,dtype=tf.float32,name="Weight")
b = tf.Variable(1.0,dtype=tf.float32,name="Bias")
x = tf.placeholder(dtype=tf.float32,name="Input")
with tf.name_scope("Output"):#输出的命名空间
	y = W * x + b

path = "./log"

#创建用于初始化所有变量(Variable)
init = tf.global_variable_initializer()

with tf.Session() as sess:
	#实现初始化操作
	sess.run(init)
	writer = tf.summary.FileWriter(path,sess.grapg)
	result = sess.run(y,{x:3.0})
	print("y = %s" % result)