import tensorflow as tf
import numpy as np
...
out = tf.layers.conv2d(x,filter_nums,filter_size,use_bias=False,
kernel_initializer=tf.truncated_normal_initializer(),
padding='same',activation=None,name = 'conv1') #函数的name
...
with tf.name_scope('input'): #空间范围的name
image_x = tf.placeholder(imagename_array.dtype,[None],name='image_x') #函数的name
label_y = tf.placeholder(label_agen_array.dtype,[None,7,7,6],name='label_y') #函数的name
istraing = tf.placeholder(tf.bool,name='istraing') #函数的name
...
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
writer = tf.summary.FileWriter('logs/',sess.graph) #'logs/'是写入路径,sess.graph表示将图写入,所以不需要训练
以上代码表示name可由with tf.name_scope(‘one name’):和tf.function(name = ‘another name’)产生。
- 首先,在with tf.name_scope(‘one name’):下缩进的opration的name带有’one name’的前缀;
- 然后,我们将图写入磁盘:writer = tf.summary.FileWriter(‘logs/’,sess.graph) ,在log文件夹下,可以发现其生成的文件,文件名如:events.out.tfevents.XXXX;
- 最后,利用tensorboard查看网络结构,在ubuntu环境下,ctrl+alt+t打开终端进入对应文件夹并执行:
tensorboard --logdir ./logs
结果如下:
TensorBoard 1.13.1 at http://chenchaopeng-System-Product-Name:6006 (Press CTRL+C to quit)
生成的一串网址一样的东西复制到浏览器打开,就可以查看网络结构了(注意不要关闭终端):
放大打开一个opration,可以发现其name对应到本文最开始的那段代码: