首先简单认识tensorboard

简单的生成tensorboard文件

#!/usr/bin/env python2# -*- coding: utf-8 -*-"""tensorboard 可视化生成tensorboard文件"""import tensorflow as tfdef add_layer(inputs, in_size, out_size, activation_function=None):    # add one more layer and return the output of this layer    Weights = tf.Variable(tf.random_normal([in_size, out_size]))    biases = tf.Variable(tf.zeros([1, out_size]) + 0.1)    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, )    return outputs# define placeholder for inputs to networkxs = tf.placeholder(tf.float32, [None, 1])ys = tf.placeholder(tf.float32, [None, 1])# add hidden layerl1 = add_layer(xs, 1, 10, activation_function=tf.nn.relu)# add output layerprediction = add_layer(l1, 10, 1, activation_function=None)# the error between prediciton and real dataloss = tf.reduce_mean(tf.reduce_sum(tf.square(ys - prediction),                                    reduction_indices=[1]))train_step = tf.train.GradientDescentOptimizer(0.1).minimize(loss)sess = tf.Session()"""tensorboard文件生成的位置,文件位置为../logs"""writer = tf.summary.FileWriter("../logs/", sess.graph)# important stepsess.run(tf.initialize_all_variables())

 

运行程序后, 可以在tensorboard文件生成的位置的文件夹下找到名为events.out.tfevents.1499943764.m类似的文件

打开终端输入:

tensorboard --logdir='../logs/'

logdir为程序中定义的log的文件夹路径

看到如下运行结果

$ tensorboard --logdir='../logs/'Starting TensorBoard 41 on port 6006

 

打开浏览器输入http://0.0.0.0:6006, 即可打开可视化界面,左下角有文件的路径

 

上面只是生成了一个界面,下面详细的定义每个tensorboard中每个标签页输出的图像