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.

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

关于contrastive pretraining strategy的提问 #9

Open
TowardsXY opened this issue Dec 9, 2021 · 0 comments
Open

关于contrastive pretraining strategy的提问 #9

TowardsXY opened this issue Dec 9, 2021 · 0 comments

Comments

@TowardsXY
Copy link

作者您好，很感激您开源了你们这份代码，但是在其中有一些没明白的点，希望您能解惑一下：
论文中提到有利用孪生模型利用MOS分之间隐含的rank信息而不是单纯对MOS分做回归，会生成一波preference probabillity与预测分数si，然后与实际的prefenrece probabillity和实际分数算cross entrophy，但是在代码中好像没有看到这个。想知道在这个策略是用在最后来验证WResNet的性能还是用作WResNet的pretraining呢？
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
Milestone
No milestone
Development

No branches or pull requests
1 participant
@TowardsXY