We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
我看论文原理,是没有强绑定sourc与target必须为同一个人的,但是在论文实验说明中,有明确说训练阶段source与target为同一id,以至于loss那块存在感知损失,且我看源码数据处理模块FramesDataset中,source与target也是同id.
因为我现在有个任务,是需要实现比较精细的不同id之间的重演,所以我想问一下,是否可以在该工程基础上训不同id的重演?希望作者能回复一下,不甚感激!
The text was updated successfully, but these errors were encountered:
在训练过程中,因为需要ground truth,所以只能在相同id下训练,如果采用不同id,那么在训练过程中,就没有对应的ground truth。
Sorry, something went wrong.
是的。我看论文有个Cross-identity reenactment小节,我以为你们针对Cross-identity 重训过。 也就是说,训练阶段,还是必须同ID训,推理和实际应用阶段,可以迁移到Cross-identity使用,是吗?
是的,但其实这样的效果在面对cross-identity的时候还是有局限性,可以参考一下x-portrait的方式,数据量上去了,问题不大,有啥问题可以一起讨论交流。
是的。好的好的,我马上去看下x-portrait原理,非常感谢指导!
No branches or pull requests
我看论文原理,是没有强绑定sourc与target必须为同一个人的,但是在论文实验说明中,有明确说训练阶段source与target为同一id,以至于loss那块存在感知损失,且我看源码数据处理模块FramesDataset中,source与target也是同id.
因为我现在有个任务,是需要实现比较精细的不同id之间的重演,所以我想问一下,是否可以在该工程基础上训不同id的重演?希望作者能回复一下,不甚感激!
The text was updated successfully, but these errors were encountered: