Fix bug in slicing of latent encodings in src/sharp/models/encoders/spn_encoder.py#82
Open
Riccardo-Rota wants to merge 1 commit intoapple:mainfrom
Open
Fix bug in slicing of latent encodings in src/sharp/models/encoders/spn_encoder.py#82Riccardo-Rota wants to merge 1 commit intoapple:mainfrom
Riccardo-Rota wants to merge 1 commit intoapple:mainfrom
Conversation
Latent encodings were sliced as x_latent0_encodings[: batch_size * x0_tile_size], changed into x_latent0_encodings[: x0_tile_size] because x0_tile_size already accounts for batch size. For example, if batch_size=10, the original x_latent0_encodings has shape [350, 1024, 24, 24] and x0_tile_size=250. If we multiply again by batch_size=10, we slice up to index 2500, making the slicing uneffective. Same happens for x_latent1_encodings
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Latent encodings were sliced as x_latent0_encodings[: batch_size * x0_tile_size], changed into x_latent0_encodings[: x0_tile_size] because x0_tile_size already accounts for batch size. For example, if batch_size=10, the original x_latent0_encodings has shape [350, 1024, 24, 24] and x0_tile_size=250. If we multiply again by batch_size=10, we slice up to index 2500, making the slicing uneffective. Same happens for x_latent1_encodings