v1.2.2 #697
Merged
v1.2.2 #697
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
* squash merge from roomrys/sleap-1 (#460) * Add test dataset with tracks * Add track indices to labels provider * Add identity class map generator * Update docstring * Add class map model trainer, head and config * Add inference * Docs and tests for identity module - Slightly modified matching to greedy-like behavior * Fix inference - Add imports to evals inference - Move the common Predictor.predict() method to base class - Fix docstrings for new inference classes - Add test model and integration test * Generate tracks from config metadata if not provided * Force typecasting in identity functions * Force boolean masking op * Clean up inference module - Move common Predictor methods to base class - Switch to `model.predict_on_batch()` for massive performance increase with `predictor.predict()`. - Enable prediction directly on arrays (slow) * Enable Qt5Agg backend only when necessary during training * Top-down supervised identity prediction (#476) * Add sizematcher to new training pipelines * Fix topdown ID visualization during training * Add LabeledFrame.tracked_instances property for filtering - Greedy checking in has_* properties * Add Labels.copy() method for creating deep copies - Works by serializing and deserializing to JSON (inefficient, but guaranteed to work since we have lots of coverage on I/O) * Extract labels with tracked instances - Add copy kwarg to extract to return deep copies - Remove user and/or untracked instances in with_user_labels_only(). Previously this functionality was blocked since we couldn't remove the instances from labeled frames without affecting the source labels. - Add remove_untracked_instances() utility for filtering out instances from the labels. * Add track filtering in LabelsReader provider - This is slightly redundant with Labels.with_user_labels_only(..., with_track_only=True) but serves as an extra guarantee that we don't train on instances without tracks accidentally, regardless of how the data is preprocessed. Can still emit "empty" frames if no instances have tracks set, however. * Add track filtering in DataReaders during training - Auto-enabled when training from ID models - Filters out instances without tracks BEFORE train/val splitting - Split is now done on copy of labels - Fix DataReaders arg typing - Tests for DataReaders * Add crop size detection to topdown ID models - Add training integration test for topdown ID * add removal of untracked instances for labeled instances (#460) * Add removal of untracked instances for labeled instances - previously used `LabeledFrame.tracked_instances()` which only returns predicted instances with tracking - created `LabeledFrame.remove_untracked` which returns both user labeled and predicted instances with tracking * Formatting - using black v20.8b1 * add tests for Labels and LabeledFrames (#460) * Add tests - test `Labels.remove_untracked_instances()` for both cases of `remove_empty_frames: bool` -test `LabeledFrames.remove_untracked()` for both user-labeled and predicted frames * formatting (#460) * add newline (no indent) at end of files which had failed Lint test * clean-up comments and unneeded parenthesis (#460) * Last merge fixes * Lint
* Expose identity module in nn * Override predict_on_batch to optionally cast data to numpy
* Fix topological sorting to always start with root node * Add test
* Training monitor enhancements - Cleaned up imports - Docstrings - Now update based on time, not epochs - Added markers for epoch-level losses - Added best validation loss marker and text - Reduced minimum possible y-axis value when log scaling - Marker colors, alpha, sizes and line widths adjusted * Move training monitor to gui submodule * add metrics to training monitor title * add mean time per epoch * add ETA to finish next 10 epochs * add plateau patience fraction (when in plateau) * update dev_requirements to install version of click that does not break black * Add code coverage * add coverage for all lines within LossViewer.update_runtime() Co-authored-by: roomrys <38435167+roomrys@users.noreply.github.com>
* Single press of hotkey (H) toggles instance visibility * Add instance visibility message/warning to status bar * Resize keyboard shortcuts dialog box
* Update formatting to include tracking_scores * Add formatting fixtures, tracking_scores test
* add hide instance menu item and hotkey * single press of hotkey (H) toggles instance visibility * Add instance visibility message to status bar * Resize keyboard shortcuts dialog box * Make shortcuts pop-up slightly narrower and taller * Hide predicted instances as well * hide predicted instances * update status bar message: - count only visible predicted and labeled instances - only show "hidden instances" warning when number instances in frame is greater than 0 - normal font weight * Logic update for detecting instances to show * Add test for instance visibility * Change which qtbot wait is used * Change timeout of qtbot.waitActive - attempt to pass ubuntu tests on github actions * Use arbitrary qtbot.wait Hope to verify that ubuntu test fails due to a waiting error * Add test for instance colors - predict ubuntu test will fail * Add test skip mark for ubuntu * Import pytest * Skip test for linux * Remove unused packages
* Change default tab appearance * Bump to 1.2.2
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.
Description
Add support for new maDLC labels format (#678)
Fix numpy conversion in inference (#687)
Fix topological sorting to always start with root node (#688)
Create unique default shortcuts (fixes #686) (#690)
Training monitor enhancements (implements #624) (#691)
Add hide instance menu item and hotkey (implements #665) (#692, #694)
Fix formatting to read and save tracking scores (#693)
Types of changes
Does this address any currently open issues?
[list open issues here]
Outside contributors checklist
Thank you for contributing to SLEAP!
❤️