score_dir#
- ibl_bwb_eval.scoring.ts1.score_dir(pred_dir, gt_dir)[source]#
Score all TS1 prediction files found under
pred_dir.Expects prediction files written by
PredictionsWriter(metadata carrieslabel,task,recording_id,seed).pred_dirmay point at any subtree (e.g. the sharedpredictions/root), files whosetaskisn’t ats1-*task are skipped.Ground truth files are looked up as:
{gt_dir}/{task}/{recording_id}/ground_truth.safetensorsReturns a dict keyed by
(label, task, recording_id, seed), where each value is a dict mapping metric name to scalar value.