Feat: Frame-level Extraction and PyTorch API Updates #41
Conversation
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
- Replace closely deprecated ConvNormActivation with Conv2dNormActivation - Update torch.stft to use return_complex=True for complex tensor handling and torch.square(torch.abs(x)) for power magnitude computation from complex-valued spectrogram - Replace torch.cuda.amp.autocast with torch.amp.autocast for better device compatibility These changes ensure compatibility with newer PyTorch versions while maintaining backward compatibility and fixing deprecation warnings.
…odels - Add 'frame' parameter to forward methods in MN and DyMN classes - Modify _clf_forward and _forward_impl methods to support frame-level feature extraction - Update adaptive pooling logic to preserve temporal dimension when frame=True - Maintain backward compatibility with existing clip-level feature extraction - Enable frame-wise embeddings output alongside classification results This enhancement allows models to extract features at frame level (preserving temporal dimension) in addition to the existing clip-level aggregation, enabling more fine-grained temporal analysis.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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 pull request introduces two main sets of changes: a new feature for frame-level embedding extraction and several updates to ensure compatibility with modern PyTorch versions by replacing deprecated APIs.
New Features:
Frame-level Feature Extraction:
Fixes & Maintenance:
PyTorch API Modernization: