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.

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

关于训练的一点疑问 #85

Open
Pepper-FlavoredChewingGum opened this issue Jan 18, 2025 · 1 comment
Open

关于训练的一点疑问 #85

Pepper-FlavoredChewingGum opened this issue Jan 18, 2025 · 1 comment

Comments

@Pepper-FlavoredChewingGum

@danpeng2 感谢回复。想再请教两个问题:

1、为什么多视图损失要在7000次迭代之后才进行,如何一开始就使用多视图损失效果如何?

2、为什么计算多视图ncc loss时,要加入torch.no_grad(),而计算其他损失则不需要?

Originally posted by @Pepper-FlavoredChewingGum in #84

@danpeng2
Copy link
Contributor

你好,
1、一开始添加多视图损失也是可以的,可能训练耗时长一些,表面更平滑一些
2、计算ncc loss时候,只在部分不需要梯度回传的运算上使用了torch.no_grad()

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants