Welcome to OGeek Q&A Community for programmer and developer-Open, Learning and Share
Welcome To Ask or Share your Answers For Others

Categories

0 votes
4.9k views
in Technique[技术] by (71.8m points)

Change performance metrics for TensorFlow 2 Object Detection API

Where do i find the config file?

The default metrics are based on those used in Pascal VOC evaluation.

To use the COCO object detection metrics add metrics_set: "coco_detection_metrics" to the eval_config message in the config file.

To use the COCO instance segmentation metrics add metrics_set: "coco_mask_metrics" to the eval_config message in the config file.

https://tensorflow-object-detection-api-tutorial.readthedocs.io/en/latest/install.html


与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
Welcome To Ask or Share your Answers For Others

1 Reply

0 votes
by (71.8m points)

If you are using a pre-trained model from the model zoo the configuration file is the pipeline.config that is in every model-archive. If you are building your own network you have to write your pipeline.config following the guidelines. So simply edit your pipeline.config adding metrics_set: "coco_detection_metrics" in the eval_config section for COCO, the same if you want PASCAL-VOC.


与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…
OGeek|极客中国-欢迎来到极客的世界,一个免费开放的程序员编程交流平台!开放,进步,分享!让技术改变生活,让极客改变未来! Welcome to OGeek Q&A Community for programmer and developer-Open, Learning and Share
Click Here to Ask a Question

1.4m articles

1.4m replys

5 comments

57.0k users

...