Tensorboard 6006端口无法访问的问题

1 、写一个简单实例，完成tensorboard 日志输出功能，示例代码如下：

import tensorflow as tf
 
input1 = tf.constant([1.0, 2.0, 3.0], name='input1')
input2 = tf.Variable(tf.random_uniform([3]), name='input2')
output = tf.add_n([input1, input2], name='add')
model  = tf.initialize_all_variables()
 
 
with tf.Session() as sess:
    merged = tf.summary.merge_all()
    writer = tf.summary.FileWriter('E:/TensorBoard/test', sess.graph )
    sess.run(model)
    print(sess.run(output))
writer.close()

2、启动tensorboard
按照教程：tensorboard --logdir=E://TensorBoard//test ，然后在浏览器中访问 127.0.0.1:6006 并不能访问。原因未知，但很多资料中这样写的。
解决方案：
cd [your log dir]

run commond tensorboard --logdir ./ --host=127.0.0.1

然后在浏览器中打开：http://127.0.0.1:6006 就可以看到了

同时加载比较多个model

tensorboard --logdir=256_256_256:v1_256_256_256_20181024_120106/,256_512_256:v1_256_512_256_20181024_120035/,256_512:v1_256_512_20181024_120237/ --host=127.0.0.1
https://stackoverflow.com/questions/36182380/how-do-display-different-runs-in-tensorboard