Conversation
added option in signal_processing.gcc to pass frequency_range args, freqs outside the range are set to zero during the cross correlation calculation this is particularly useful when using gcc-phat and high-frequency phase information is causing spurious high correlation values at the edges or at a delay of 0. added test for this arg in test_gcc smoke test
resolves Loading a saved shallow classifier Fixes #1143 makes MLPClassifier.load() a class method, loads a dictionary saved with MLPClassifier.save() move _version_mistmatch_warn() to utils for use across modules
resolves support using or modifying MLPClassifier in SpectrogramModule.change_classes Fixes #1145 also adds relevant tests
include per-class auroc
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Gcc with bandpass
resolve returning Audio from cell can cause un-normalized error Fixes #1118
resolve SpatialEvent can be created without properties needed for .localize() Fixes #1124
this is faster and will improve compatability with exporting PyTorch models to ONNX Still need to implement a batched version of spectrogram creation for preprocessing, and demonstrate how to export models for ONNX with the spectrogram creation included in the model
resolves cannot pass sample_width or sample_height to SpectrogramPreprocessor() or CNN() init Fixes #1162
… single value rather than as a list of character-level labels Fixes #1153
also fix docstring Docstring in localize_detections incorrectly states detections should be a dictionary, when it should be a dataframe Fixes #1126
Improvements to MLPCLassifier saving
failed-to-process samples still get scores because of bug when num_workers>0 Fixes #1180
Spec refactor
Proposed fix for #1205 - using the `warnings.catch_warnings()` context manager instead of resetting warnings globally.
imagenet1k_v2 is not available for resnet18
Issue 1205: use catch_warnings context instead of global warning reset
…val_fix Standardize receiver arrays after removing bad receivers
applies a function to windowed audio segments and returns result on each window
resolves Audio.extend centering Fixes #1217
use torch.as_tensor pattern resolves #1121
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
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.
No description provided.