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
你好,感谢开源C2L网络,我在运行的时候遇到了一个问题,NCE文件夹里面的NCECriterion.py文件的57行log_D1 = torch.div(P_pos, P_pos.add(m * Pn + eps)).log_()中的“eps”变量是如何得到的?
The text was updated successfully, but these errors were encountered:
Sorry for my late reply.
In fact, I did not meet this problem when running my code. I suggest you to set eps to a very small value, such as 1e-6.
Hope it can help you.
Sorry, something went wrong.
您好,我也遇见了同样的问题,请问您是怎么解决的呀
遇到了同样的问题,按照作者建议,使用1e-6代替了。此外代码中的n_data怎么理解呢?每个epoch迭代的次数吗?还是总数据量,C2L代码中写len(train_dataset),PCRL写len(train_dataloader),希望作者能够解答一下,谢谢
No branches or pull requests
你好,感谢开源C2L网络,我在运行的时候遇到了一个问题,NCE文件夹里面的NCECriterion.py文件的57行log_D1 = torch.div(P_pos, P_pos.add(m * Pn + eps)).log_()中的“eps”变量是如何得到的?
The text was updated successfully, but these errors were encountered: