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
Hi, I think there's an error in AvgReadout with a mask. The mask summation should be performed along the first dimension only.
AvgReadout
DGI/layers/readout.py
Line 15 in 0afce4e
It is return torch.sum(seq * msk, 1) / torch.sum(msk) but should be return torch.sum(seq * msk, 1) / torch.sum(msk, 1) # Note the dimension here.
return torch.sum(seq * msk, 1) / torch.sum(msk)
return torch.sum(seq * msk, 1) / torch.sum(msk, 1) # Note the dimension here.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Hi, I think there's an error in
AvgReadoutwith a mask. The mask summation should be performed along the first dimension only.DGI/layers/readout.py
Line 15 in 0afce4e
It is
return torch.sum(seq * msk, 1) / torch.sum(msk)but should be
return torch.sum(seq * msk, 1) / torch.sum(msk, 1) # Note the dimension here.The text was updated successfully, but these errors were encountered: