improve Dataset class, avoiding all the 'if condition: continue' and allow deterministic idx #16
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Outdated suggestions cannot be applied.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.
In the file
train_vocalist_lrs2.py
, in the__getitem__
method of the Dataset class, an idx index was drawn at random, even though idx was supplied as input to the method. As a result, a while True is required and a lot of conditions that lead to acontinue
if they are not met. I replaced all this withassert not condition
, which allowed me to debug the Dataset class.This has been done in
train_vocalist_lrs2.py
and could be extended totrain_vocalist_acappella.py
(if the PR is accepted).Note small changes in
train
andeval_model
functions (cosmetic).