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

Data leakage #1

Open

xbh0720 opened this issue Nov 22, 2021 · 1 comment

xbh0720 commented Nov 22, 2021

alphas=nn.Softmax(dim=1)(att_w)
should be masked

xbh0720 closed this as completed

xbh0720 reopened this

lilstrawberry commented Aug 4, 2023

Yes, the future information is used when calculating the attention value of each state of the sequence, resulting in inflated performance

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment