tensorflow - 如何查找卡住模型的输入和输出节点

Question

我想在模型动物园中的卡住模型上使用tensorflow的optimize_for_inference.py脚本:ssd_mobilenet_v1_coco。

如何查找/确定模型的输入名称和输出名称？

Hires version of the graph generated by tensorboard

这个问题可能有帮助:Given a tensor flow model graph, how to find the input node and output node names (对我来说没有)

Answer 1

我认为你可以使用以下代码。我从 here 下载了 ssd_mobilenet_v1_coco 卡住模型并能够获取输入和输出名称，如下所示

!pip install tensorflow==1.15.5

import tensorflow as tf
tf.__version__ # TF1.15.5

gf = tf.GraphDef()  
m_file = open('/content/frozen_inference_graph.pb','rb')
gf.ParseFromString(m_file.read())
 
with open('somefile.txt', 'a') as the_file:
   for n in gf.node:
       the_file.write(n.name+'\n')
 
file = open('somefile.txt','r')
data = file.readlines()
print("output name = ")
print(data[len(data)-1])
 
print("Input name = ")
file.seek ( 0 )
print(file.readline())

输出为

output name = 
detection_classes

Input name = 
image_tensor

请检查gist here .