This is something you do as part of the post-processing. You receive landmarks in normalized coordinates and you need to compute them in the original image resolution.
Here is an example of how it's done:
https://github.com/axinc-ai/ailia-models/blob/master/pose_estimation/blazepose/blazepose.py#L212
Distraction-free reading. No ads.
Organize your knowledge with lists and highlights.
Tell your story. Find your audience.
Read member-only stories
Support writers you read most
Earn money for your writing
Listen to audio narrations
Read offline with the Medium app
Engineer with 10+ years in game engines & multiplayer backend development. Now focused on machine learning, computer vision, graphics and AR
