在 tensorflow 中将 SSD 转换为冻结图.必须使用哪些输出节点名称? [英] Converting SSD to frozen graph in tensorflow. Which output node names must be used?

问题描述

我使用 TensorFlow 对象检测 API 训练了 SSD 如此处所述.它生成 ckpt、meta 和 index 文件.为了在我的图像上运行它，我尝试检查演示代码.它要求将模型转换为冻结图.我尝试将我的模型转换为冻结的推理图，如此处所述.在那个程序中，我必须提供输出节点名称.我无法弄清楚此处必须使用的 SSD 模型中节点的名称.请帮忙.我试过 'num_detections:0', 'detection_boxes:0' 等，结果却出错:

I trained SSD using TensorFlow Object Detection API as described here. It produces a ckpt, meta and index file. In order to run it on my images I tried to check the demo code. It requires that the model be converted to frozen graph. I tried to convert my model to a frozen inference graph as described here. In that program I have to provide output node names. I could not figure out the name of the node in the SSD model which must be used here. Please help. I tried 'num_detections:0', 'detection_boxes:0' etc. Only to get error:

断言错误:num_detections 不在图表中

AssertionError: num_detections is not in graph

推荐答案

我们有一个特殊的工具可以在 Tensorflow 对象检测 API 中转换为冻结图 --- 只需运行 export_inference_graph.py 二进制.使用此工具的说明位于此处.

We have a special tool to convert to frozen graphs in the Tensorflow Object Detection API --- just run the export_inference_graph.py binary. Directions for using this tool are here.

这篇关于在 tensorflow 中将 SSD 转换为冻结图.必须使用哪些输出节点名称?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！