8000 Questions about data preprocess of VFHQ · Issue #15 · YuDeng/Portrait-4D · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Questions about data preprocess of VFHQ #15

New issue

Have a question about this project? Sign up for a free GitHub account to open an is 8000 sue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom
Open
Time-Lord12th opened this issue Dec 13, 2024 · 4 comments
Open

Questions about data preprocess of VFHQ #15

Time-Lord12th opened this issue Dec 13, 2024 · 4 comments

Comments

@Time-Lord12th
Copy link

Thanks for your great work!
I have some questions about data preprocess of VFHQ.

  1. Do you use flame_optim_batch_singleframe.py or flame_optim_batch_multiframe.py for full BFM-to-FLAME transformation process?
  2. For face segmenation using Mask2Former, which trained model should I choose?
  3. If possible, can you tell me the time cost of VFHQ preprocessing？

Thanks!
@gangxu822
Copy link

+1 same question

@gangxu822
Copy link
https://github.com/facebookresearch/Mask2Former/blob/9b0651c6c1d5b3af2e6da0589b719c514ec0d69a/MODEL_ZOO.md

i use this conf and model,match is import

@gangxu822
Copy link

Image

@gangxu822
Copy link

python demo.py --config-file ../configs/coco/panoptic-segmentation/maskformer2_R50_bs16_50ep.yaml \
--input "$input_path"
--output "$output_path"
--opts MODEL.WEIGHTS ./model_final_94dc52.pkl

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@gangxu822 @Time-Lord12th
0