Fix bug related to SoftDTWLossPytorch with option normalize=True when used on inputs of different lengths #478
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR is related to the issue #473 reporting an error message when
SoftDTWLossPytorch
with optionnormalize=True
is used on inputs of different lengths.The bug is coming from the use of
torch.cat
(https://pytorch.org/docs/stable/generated/torch.cat.html) which impose the lengths of the inputs to be equal. (The shape of the inputs is[batch_size, length, dim]
.)The use of
torch.cat
is removed in this PR.