OpenTalker / StyleHEAT

[ECCV 2022] StyleHEAT: A framework for high-resolution editable talking face generation
MIT License
627 stars 77 forks source link

some inconsistent in code #29

Closed yqwang closed 1 year ago

yqwang commented 1 year ago

Very appreciate your great work. I maybe found two inconsistent in code when i try to retrain the video warper, but not very uncertainly and hope to make check it.

  1. https://github.com/FeiiYin/StyleHEAT/blob/bad7f124a74028ee4f425428388bb1e350a5119e/trainers/video_warper_trainer.py#L88 I found there is no key 'final_image' in all network forward return results.
  2. https://github.com/FeiiYin/StyleHEAT/blob/bad7f124a74028ee4f425428388bb1e350a5119e/trainers/video_warper_trainer.py#L87 parameters is not equal to defined in VideoWarper::forward
FeiiYin commented 1 year ago

Thanks for your attention! It seems there exist several testing codes in the repo. The final_image is used for mixing two warping processes but is not in use in the end. There exist only one output of the video warper. You can delete the code about the final_image and only use the warping_field to warp the original image or feature.

yqwang commented 1 year ago

Thanks for your attention! It seems there exist several testing codes in the repo. The final_image is used for mixing two warping processes but is not in use in the end. There exist only one output of the video warper. You can delete the code about the final_image and only use the warping_field to warp the original image or feature.

Thanks, got it.