Open
Conversation
This script: - Loads JIT-compiled ResNet embedding model - Processes continuous strain data from h5 files - Applies whitening and bandpassing (matching training) - Segments data into 1-second windows - Computes embeddings for each window - Handles BBC background (with valid clean times) and O4 signals - Saves embeddings to HDF5 files Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Documents usage, arguments, workflow, and data formats for the compute_embeddings.py script. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This script: - Loads computed embeddings from HDF5 or .npy files - Loads reference embeddings for comparison - Computes mean and std for each embedding dimension - Compares statistics and reports differences - Checks similarity within tolerance - Provides detailed dimension-by-dimension comparison Usage: python scripts/test_embeddings.py --computed output/embeddings/o4_test_embeddings.h5 python scripts/test_embeddings.py --help Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Issues fixed: - Validate that valid_times have enough data BEFORE them for PSD - Add explicit segment size validation before stacking - Skip segments that don't have expected number of samples - Prevent empty batches from being processed This fixes "Number of samples 0 in input x is insufficient for number of fft samples 8192" errors at file boundaries. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changes all default path arguments and documentation to use gwak/output/ instead of output/ to match the actual directory structure on the cluster. Files updated: - scripts/compute_embeddings.py: Default args for model, data dirs, output - scripts/test_embeddings.py: Auto-detect paths - scripts/README.md: Documentation examples Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Corrects the default model path to use ResNet_HL instead of ResNet_HK to match the actual model directory. Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This script calculates signal detection efficiencies by: - Converting embedding trigger indices to GPS times - Matching triggers to injections from h5 injection files - Computing efficiency vs SNR for each signal type - Generating efficiency plots and summary statistics Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Collaborator
Author
|
@AndyC80297, why are all the embedding-related new files from you not in the main? I can't figure out why they are in my branch, but are not in main... |
Closed
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
3 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.
Uh oh!
There was an error while loading. Please reload this page.