pip

aucpr.py

@@ -15,7 +15,7 @@
 
 import evaluate
 import datasets
-from sklearn.metrics import precision_recall_curve, auc
+from sklearn.metrics import precision_recall_curve, auc, average_precision_score
 
 
 # TODO: Add BibTeX citation
@@ -93,9 +93,11 @@ class AUCPR(evaluate.Metric):
 
     def _compute(self, references, prediction_scores):
         """Returns the scores"""
-        # TODO: Compute the different scores of the module
+        # following: https://github.com/jertubiana/ScanNet/blob/7685549c8ed2159a0f441a977dec767343256292/baselines/train_handcrafted_features_PPBS.py#L47
+        # instead of using average_precision_score
         precision, recall, _ = precision_recall_curve(references, prediction_scores)
         aucpr = auc(recall, precision)
+#         aucpr = average_precision_score(references, prediction_scores)
         return {
             "aucpr": aucpr,
         }