tensorflow 输出pre_trained模型网络层名称以及数据

tensorflow 输出pre_trained模型网络层名称以及数据

在模型训练或者模型使用过程中，往往要获取相关层的名称或者特征，下面介绍如何读取pre_trained model的各层数据以及各层的命名，以inception-v3模型为例。

• 1、预训练模型下载

import numpy as np  
import tensorflow as tf  
import download  
from cache import cache  
import os  
import sys  

########################################################################  
# 压缩包地址.  
data_url = "http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz"  

# 数据保存地址.  
data_dir = "inception/"  

# ImageNet 各个分类的名称. (Downloaded)  
path_uid_to_cls = "imagenet_2012_challenge_label_map_proto.pbtxt"  

# File containing the mappings between uid and string. (Downloaded)  
path_uid_to_name = "imagenet_synset_to_human_label_map.txt"  

# 网络层定义. (Downloaded)  
path_graph_def =