OpenGVLab/Hulk

Questions about the practical application of Hulk

Bo396543018 opened this issue · 2 comments

Thank you for your great work.
I have a question about practical inference. Is it necessary to infer twice for keypoint, first by detection to crop the human body and then to infer the key points?

If the input image contains multiple people, the answer is yes.

Following UniHCP, Hulk is a top-down method for the 2D pose estimation task. Therefore, you need to detect the person first by inferencing Hulk.

Get, thank you for your answer.