penincillin / ihmr Goto Github PK

1. In the training, I found the camera params (s, tx, ty) seems not converge, but the mano params could converge normaly. I checked the dataset (freihand and interhand), the camera's focal length differs with each image, and it range from 400mm to 800mm. I wonder if the diversity of focal length in the dataset makes it converge worse?

2. Also, the solution may be adjusting the loss weight in the training process? just as u do /src/strategies/opt_default.py. I wonder how the converge order, what i mean is which parmas should converge first or last?

3. The camera params GT and camera loss isnot found in your project, should I remove the camera loss too?

I can't find the file ry_utils.py, how can I get this file please?

what's the difference between hand26m your offered and official？I have download the interhand2.6M from official, is it necessary to download again from your url?

in the data_processor.random_rotate(), the returned joint2d is right:

however the returned joint3d is weird:

and the returned mano output is :

I'm trying to test the dataset but I can't find 'ry_utils.py' in any folder, and I got an error that 'ModuleNotFoundError: No module named 'ry_utils'', could you please offer some advice to help me solving this problem? Thank you.