Draft: Experimental SigMF Recording Import #406
Closed
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
Collaborator
|
Thank you! Discussing this internally. |
- Introduced a new method `_load_label_mapping` to load label mappings from the dataset YAML file. - Added a `label_mapping` attribute to store the mapping of class indices to class names. - Updated the `prepare_data` method to call `_load_label_mapping` after initializing the dataset. - Enhanced type hints by importing `Dict` for better clarity on the label mapping structure.
Collaborator
|
@romanziske Thanks for writing this up but we've got an internal solution for SigMF coming up for our 2.0 release. It handles some of the changes to NB/WB (and other things) that we've made as part of this new release. You'll see a notebook in the new release that describes how to read from SigMF files and other data types for importing data into torchsig. I've made a note to credit you as part of the 2.0 release for helping seed us for the SigMF development. We're quite close, expect a release in terms of weeks or days. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Draft: Experimental SigMF Recording Import
This PR adds experimental support for importing SigMF recordings into TorchSig. It is intentionally a draft to illustrate how TorchSig could support SigMF datasets.
Wideband conversion creates overlapping time-domain chunks from continuous SigMF data where each sample can contain multiple concurrent signals.
Narrowband conversion extracts individual signal annotations as separate samples, applies frequency filtering to isolate each signal, and adds them to a generated noise floor with controlled SNR.
