if class-specific, also log average/sum over all classes to make it easier to get an idea of metric

det-metrics.py

@@ -457,10 +457,15 @@ class DetectionMetric(evaluate.Metric):
                                         (f"{(wandb_section + '/') if wandb_section else ''}{cls_name}/{area_range + '.' + m}") : v[cls_idx]
                                     }
                                 )
+                            run.log(
+                                {
+                                    (f"{(wandb_section + '/') if wandb_section else ''}all/{area_range + '.' + m}") : v[v != -1].sum() if m in ["duplicates", "support"] else v[v != -1].mean()
+                                }
+                            )
                         else:
                             run.log(
                                 {
-                                    f"{(wandb_section + '/') if wandb_section is not None else ''}{m}" : v
+                                    f"{(wandb_section + '/') if wandb_section is not None else ''}{area_range + '.' + m}" : v
                                 }
                             )
             if wandb_runs is None: