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.

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

Fix 'TypeError' of rnnt_loss_pruned function. #924

Merged
merged 7 commits into from
Feb 27, 2022
Merged

Fix 'TypeError' of rnnt_loss_pruned function. #924

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
64361ad
Fix 'TypeError' of rnnt_loss_simple function.
drawfish Feb 22, 2022
4479049
Merge branch 'k2-fsa:master' into master
drawfish Feb 23, 2022
a7cc32c
Fix 'MutualInformationRecursionFunction.forward()' return type check …
Feb 23, 2022
2eeabe6
Modify return type.
Feb 23, 2022
b208a4f
Add documents about class MutualInformationRecursionFunction.
Feb 23, 2022
0697c64
Formated code style.
Feb 23, 2022
acdbb2a
Fix rnnt_loss_smoothed return type.
drawfish Feb 24, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
Fix 'TypeError' of rnnt_loss_simple function. 
Fix 'TypeError' exception when calling rnnt_loss_simple(..., return_grad=False)  at validation steps.
  • Loading branch information
@drawfish
drawfish authored Feb 22, 2022
commit 64361adef294de7dfced4229604c585f59b89aff
2 changes: 1 addition & 1 deletion k2/python/k2/mutual_information.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ def forward(

ans = _k2.mutual_information_forward(px, py, boundary, p)

px_grad, py_grad = None, None
px_grad, py_grad = torch.Tensor(), torch.Tensor()
if return_grad or px.requires_grad or py.requires_grad:
ans_grad = torch.ones(B, device=px.device, dtype=px.dtype)
(px_grad, py_grad) = _k2.mutual_information_backward(
Expand Down