[Question] How to preprocess images when using RTMPose Face models?

open-mmlab / mmpose

OpenMMLab Pose Estimation Toolbox and Benchmark.

https://mmpose.readthedocs.io/en/latest/

Apache License 2.0

5.82k stars 1.24k forks source link

[Question] How to preprocess images when using RTMPose Face models? #2538

Closed deep-practice closed 1 year ago

deep-practice commented 1 year ago

📚 The doc issue

How to preprocess images when using RTMPose Face models?When I simply crop the face region as the input,the result is not so good.

Suggest a potential alternative/fix

No response

Tau-J commented 1 year ago

Thanks for using MMPose. We will multiply the length and width of the face bbox by 1.25 for expansion, and use the expanded bbox for cropping as the input to the model.

deep-practice commented 1 year ago

Got it