Skip to content

Fix documentation for attention mask shape #20850

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

Closed
jotsif wants to merge 1 commit into from
Closed

Fix documentation for attention mask shape #20850

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion torch/nn/functional.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3126,7 +3126,7 @@ def multi_head_attention_forward(query, # type: Tensor
- value: :math:`(S, N, E)` where S is the source sequence length, N is the batch size, E is
the embedding dimension.
- key_padding_mask: :math:`(N, S)`, ByteTensor, where N is the batch size, S is the source sequence length.
- attn_mask: :math:`(L, L)` where L is the target sequence length.
- attn_mask: :math:`(L, S)` where L is the target sequence length, S is the source sequence length.

Outputs:
- attn_output: :math:`(L, N, E)` where L is the target sequence length, N is the batch size,
Expand Down
2 changes: 1 addition & 1 deletion torch/nn/modules/activation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -764,7 +764,7 @@ def forward(self, query, key, value, key_padding_mask=None,
- value: :math:`(S, N, E)` where S is the source sequence length, N is the batch size, E is
the embedding dimension.
- key_padding_mask: :math:`(N, S)`, ByteTensor, where N is the batch size, S is the source sequence length.
- attn_mask: :math:`(L, L)` where L is the target sequence length.
- attn_mask: :math:`(L, S)` where L is the target sequence length, S is the source sequence length.

- Outputs:
- attn_output: :math:`(L, N, E)` where L is the target sequence length, N is the batch size,
Expand Down