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

训练的时候,没有负样本么? #6

Open
wentixiaogege opened this issue Apr 1, 2021 · 4 comments
Open

训练的时候,没有负样本么? #6

wentixiaogege opened this issue Apr 1, 2021 · 4 comments

Comments

@wentixiaogege
Copy link

如题,可否加一下你的kaggle,可以给你share一下我跑通的例子;
顺便能否解答一下我的疑惑?

@wentixiaogege
Copy link
Author

self.target = torch.tensor(np.diag([1.0]*bs)).cuda() ---》 只有正样本

@chengxuanying
Copy link
Owner

给n个配对的(txt,img) pair,txt的正样本只有这个img,其他的img都是负样本;img的正样本只有这个txt,其他的txt都是负样本。

@wentixiaogege
Copy link
Author

所以说,其实train还是做了一些 负采样的方式的,并没有公开对吧?

@chengxuanying
Copy link
Owner

谷歌一下双塔模型的负采样?

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