score_file# ibl_bwb_eval.scoring.ts2.score_file(pred_path, gt_path)[source]# Score one prediction file against its ground truth file. Predictions and ground truth are aligned by window_timestamps. Parameters: pred_path (Path) – Path to a seed_N.safetensors prediction file. gt_path (Path) – Path to the matching ground_truth.safetensors file. Return type: dict[str, float] Returns: Dict mapping metric name to scalar value.
