Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

render.py - Why should we transfer the .npz to .json ? #67

Open
yangxiaoleyxl opened this issue Jul 13, 2024 · 0 comments
Open

render.py - Why should we transfer the .npz to .json ? #67

yangxiaoleyxl opened this issue Jul 13, 2024 · 0 comments

Comments

@yangxiaoleyxl
Copy link

render.py lines 174 -180

" meta = json.load(open(os.path.join(seq, 'meta',
os.path.basename(anno_p).replace('.npz', '.json')
)))

    bbox_size = meta['bbox'][2] * meta['bbox'][3]
    focal_length = meta['focal']
    principal_point = meta['princpt']" 

It seems thats the .npz file (inference results) does not contain 'bbox' ,'focal' and other pose parameters, it contains these 10 parameters
" smplx_shape = {'betas': (-1, 10), 'transl': (-1, 3), 'global_orient': (-1, 3),
'body_pose': (-1, 21, 3), 'left_hand_pose': (-1, 15, 3), 'right_hand_pose': (-1, 15, 3),
'leye_pose': (-1, 3), 'reye_pose': (-1, 3), 'jaw_pose': (-1, 3), 'expression': (-1, 10)} "

how to understand the "meta" variable ?

Thanks ! :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant