Improved Tensor Dimension Handling in predict_masks
Method for fine tuning
#580
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Outdated suggestions cannot be applied.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.
close #581
Introduction of Conditional Check:
predict_masks
method, a conditional check is introduced to ascertain whether theimage_embeddings
tensor's batch size aligns with that oftokens
.if image_embeddings.shape[0] != tokens.shape[0]:
) is crucial as it guides the subsequent operation:torch.repeat_interleave
.Usage of
torch.repeat_interleave
:torch.repeat_interleave
is utilized to expand theimage_embeddings
tensor along the batch dimension to match the batch size oftokens
, ensuring consistency in tensor dimensions as the method progresses.torch.repeat_interleave
is applied directly, potentially leading to misalignments in tensor dimensions if the batch sizes are already aligned.Ensuring Consistency:
torch.repeat_interleave
is applied only when necessary, preventing potential dimension misalignment and ensuring consistent tensor handling within thepredict_masks
method.