-
Notifications
You must be signed in to change notification settings - Fork 505
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
论文和代码训练好像没对上 #39
Comments
The textual prompt control mentioned in the paper doesn't seem to be implemented in the current public version as well. Is there any plan to release the complete implementation including this feature? |
你好,非常抱歉,给你带来误导。
|
Thanks for you attention. Please stay tuned for update. |
(1)但是如果第一阶段没有训练audio的话,那么为什么audioproj.requires_grad_(False)? |
抱歉 有可能确实上传错了 稍等我check一下 |
@cuijh26 |
@cuijh26 |
在线等回复 |
@cuijh26 是与不是辛苦大佬们给个回复,粗略看了下代码,感觉跟论文相差比较大 |
I THINK IT IS A WRONG CODE OF TRAIN |
(1)第一阶段的输入在论文中是使用参考帧,音频和目标帧

但是现在的代码好像还是hallo1的:https://github1s.com/fudan-generative-vision/hallo2/blob/HEAD/hallo/datasets/mask_image.py#L132-L139
(2)可能是你没有更新第一阶段训练代码的原因,我不理解第二阶段训练的时候为什么权重保存格式net-3000.pth从哪里获得,其次是audio如果是用第一阶段的话显然是没有经过训练的
The text was updated successfully, but these errors were encountered: