如何找到特定 tensorflow 网络的 output

本文介绍了如何找到特定 tensorflow 网络的 output_node_names?的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

限时送ChatGPT账号..

我正在使用 MobileNetv2，并使用 deeplab 作为预处理器(如果这是正确的术语?).我已经完成了迁移学习以在我自己的数据集上训练示例网络，创建了 .meta、.index 和 .pbtxt 文件.当我尝试将这些转换为 pb 文件时，我遇到了许多问题.

I am working with MobileNetv2, and using deeplab as the preprocessor (if that's the right term?). I have done transfer learning to train the example network on my own dataset, creating .meta, .index and .pbtxt files. When I try to convert these to a pb file, I have hit a number of problems.

freeze_graph.py 需要知道 output_node_names.如果我使用 InceptionV3 而不是 deeplab，那就是InceptionV3/Predictions/Reshape_1".在其他地方，我看到人们使用softmax".

freeze_graph.py needs to know the output_node_names. If I were using InceptionV3 instead of deeplab, that would be "InceptionV3/Predictions/Reshape_1". Elsewhere I have seen people use "softmax".

我尝试用

I have tried listing the node names with

print([node.name for node in graph.as_graph_def().node])

print([node.name for node in graph.as_graph_def().node])

但是那个列表太长了.搜索预测"、输出"、重塑"、softmax"的变体并没有发现任何有希望的东西.

but that list is way too long. Searching for variations of "prediction", "output", "reshape", "softmax" didn't reveal anything promising.

我查看了张量板，但我对图表的复杂性感到不知所措.我找不到任何看起来像输出节点的东西.

I had a look on the tensorboard, but I was overwhelmed by the complexity of the diagram. I couldn't find anything which looked like an output node.

有些人建议使用 bazel，但当我尝试时

Some people suggest bazel, but when I tried

bazel 构建 tensorflow/tools/graph_transforms:summarize_graph

bazel build tensorflow/tools/graph_transforms:summarize_graph

我明白

ERROR: no such package 'tensorflow/tools/graph_transforms': BUILD file not found on package path`

如果相关，我使用 mobilenetv2_coco_voc_trainaug 检查点作为从 https://github/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md

in case it is relevant, I used the mobilenetv2_coco_voc_trainaug checkpoint as the starting point for my transfer learning from https://github/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md

推荐答案

鉴于生成图的代码是 在github上，我只是从头开始构建它并检查最终名称.

Given that the code to generate the graph is on github, I'd just construct it from scratch and check the final name.

import tensorflow as tf
# you'll need `models/research/slim` on your PYTHONPATH FOR THE FOLLOWING
from nets.mobilenet import mobilenet_v2

image = tf.zeros((1, 224, 224, 3), dtype=tf.float32)  # values don't matter
out, endpoints = mobilenet_v2.mobilenet(image)
print(out.name)

这篇关于如何找到特定 tensorflow 网络的 output_node_names?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！