TensorFlow查看输入节点和输出节点名称

TensorFlow 定义输入节点名称input_name： 

  with tf.name_scope('input'):
    bottleneck_input = tf.placeholder_with_default(
        bottleneck_tensor,
        shape=[batch_size, bottleneck_tensor_size],
        name='Mul')

TensorFlow查看pb数据库里面的输入节点和输出节点：

import tensorflow as tf
import os

model_dir = './tmp/'
model_name = 'output_graph.pb'

def create_graph():
    with tf.gfile.FastGFile(os.path.join(
            model_dir, model_name), 'rb') as f:
        graph_def = tf.GraphDef()
        graph_def.ParseFromString(f.read())
        tf.import_graph_def(graph_def, name='')

create_graph()
tensor_name_list = [tensor.name for tensor in tf.get_default_graph().as_graph_def().node]
for tensor_name in tensor_name_list:
    print(tensor_name,'\n')

 

如果用tensorboard 观看，训练好模型后，cd到模型训练过程存储的路径下，运行

tensorboard --logdir logs/fit

切换到GRAPHS栏，点击自己的网络图的层节点，既可以看到对应的输入和输出