Pinned issues
Issues
- 10
BUG: `vak.train_classification` throws KeyError when checking for dataset_config["params"]["target_type"]
#779 opened by henricombrink - 0
- 0
- 0
chore: fix broken CI
#783 opened by NickleDave - 0
DEV/TEST/CI: nox sessions 'tar-generated-test-data' not working as expected
#764 opened by NickleDave - 1
ENH: Add extra "expt-tracking" that uses mlflow
#778 opened by NickleDave - 0
- 1
- 1
- 1
- 0
- 0
- 0
ENH: Add functionality to set seed
#772 opened by NickleDave - 0
BUG: train_test_dur_split_inds can return indices for training set slightly smaller than target duration
#771 opened by NickleDave - 6
BUG: Error with dataset_path parameter in vak eval
#768 opened by mpescaru - 0
DEV: Bump lower bound on requires-python to 3.10
#762 opened by NickleDave - 0
- 0
MODEL: Add AVN Similarity
#760 opened by NickleDave - 0
MODEL: Add Repertoire Embedder
#759 opened by NickleDave - 0
MODEL: Add SqueakOut
#758 opened by NickleDave - 0
ENH: Add pre-trained model checkpoints
#756 opened by NickleDave - 1
ENH: Add datasets module with BioSoundSegBench
#754 opened by NickleDave - 2
- 1
BUG: Loss and metrics are not logged correctly
#726 opened by NickleDave - 2
BUG/CLN: Refactor model abstraction so we don't subclass LightningModel, to fix loss logging
#737 opened by NickleDave - 2
BUG: Running lightning with default strategy 'DDP' breaks learncurve function
#742 opened by NickleDave - 2
BUG: Predict throws `KeyError`
#745 opened by avanikop - 0
Consider switching to keras as engine
#751 opened by NickleDave - 1
ENH: Add `dataset` sub-table to config file, remove other dataset/transform param keys
#748 opened by NickleDave - 0
ENH: Add segmentation metrics
#744 opened by NickleDave - 0
TST/CLN: Add tests for transforms sub-package
#743 opened by NickleDave - 2
Out of memory error
#741 opened by athenasyarifa - 3
Error running vak prep
#740 opened by athenasyarifa - 6
Error when running vak prep train.toml
#739 opened by harshidapancholi - 5
- 8
BUG/DOC: Tutorial eval and predict configs missing sections with model names
#734 opened by harshidapancholi - 0
chore: release checklist
#733 opened by NickleDave - 3
- 0
ENH: check that value for validation step is valid for frame classification models before running learning curve
#730 opened by NickleDave - 0
- 0
CLN: Move `vak.common.trainer` into `frame_classification` / have per-model family trainers
#728 opened by NickleDave - 0
- 2
- 5
BUG: predict raises KeyError when config file is missing `[PREDICT.transform_kwargs]` with `window_size` option
#725 opened by wendtalexander - 0
- 0
BUG: Fix model families to log train loss on step
#720 opened by NickleDave - 1
ENH: Minimize duplication of data when preparing datasets for frame classification models
#717 opened by NickleDave - 0
ENH: Have `vak.predict` accept `post_tfm_kwargs` like `eval` + `learncurve`
#714 opened by NickleDave - 3
ENH: Require that `metrics` for a model definition be a subclass of `torchmetrics.Metric`
#707 opened by NickleDave - 1