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
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?
The text was updated successfully, but these errors were encountered:
self.target = torch.tensor(np.diag([1.0]*bs)).cuda() ---》 只有正样本
Sorry, something went wrong.
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。
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?
谷歌一下双塔模型的负采样?
No branches or pull requests
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?
The text was updated successfully, but these errors were encountered: