Merge pull request #572 from hglee98/fix-mAP

[!HOTFIX] handle when there is no prediction

CHANGELOG.md

@@ -18,7 +18,7 @@
 - Fix keyword error of segmentation training by `@illian01` in [PR 551](https://github.com/Nota-NetsPresso/netspresso-trainer/pull/551)
 - Fix typo when saving optimizer state_dict by `@hglee98` in [PR 553](https://github.com/Nota-NetsPresso/netspresso-trainer/pull/553)
 - Fix not initialized save_dtype error by `@hglee98` in [PR 565](https://github.com/Nota-NetsPresso/netspresso-trainer/pull/565)
-- Fix mAP error in case of certain classes object is not in the dataset `@hglee98` in [PR 571](https://github.com/Nota-NetsPresso/netspresso-trainer/pull/571)
+- Fix mAP error in case of certain classes object is not in the dataset `@hglee98` in [PR 571](https://github.com/Nota-NetsPresso/netspresso-trainer/pull/571), [PR 572](https://github.com/Nota-NetsPresso/netspresso-trainer/pull/572)
 
 ## Breaking Changes:
 

src/netspresso_trainer/metrics/detection/metric.py

@@ -161,10 +161,18 @@ def average_precisions_per_class(
     for class_idx, class_id in enumerate(unique_classes):
         is_class = prediction_class_ids == class_id
         total_true = class_counts[class_idx]
+        total_predictions = is_class.sum()
 
         if total_true == 0:
             continue
 
+        if total_predictions == 0:
+            for iou_level_idx in range(matches.shape[1]):
+                average_precisions[
+                    int(class_id), iou_level_idx
+                ] = 0.0
+            continue
+
         false_positives = (1 - matches[is_class]).cumsum(0)
         true_positives = matches[is_class].cumsum(0)
         recall = true_positives / (total_true + eps)