wandb fix

user-friendly-metrics.py

@@ -82,16 +82,14 @@ class UserFriendlyMetrics(evaluate.Metric):
             citation=_CITATION,
             inputs_description=_KWARGS_DESCRIPTION,
             # This defines the format of each prediction and reference
-            features=datasets.Features(
-                {
-                    "predictions": datasets.Sequence(
-                        datasets.Sequence(datasets.Value("float"))
-                    ),
-                    "references": datasets.Sequence(
-                        datasets.Sequence(datasets.Value("float"))
-                    ),
-                }
-            ),
+            features=datasets.Features({
+                "predictions": datasets.Sequence(
+                                datasets.Sequence(datasets.Value("float"))
+                            ),
+                "references": datasets.Features({ "all":
+                                datasets.Sequence(datasets.Sequence(datasets.Value("float")))}
+                            )
+            }), #couldn't get this to work
             # Additional links to the codebase or references
             codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
             reference_urls=["http://path.to.reference.url/new_module"],
@@ -155,7 +153,7 @@ class UserFriendlyMetrics(evaluate.Metric):
                 
                 predictions, references = payload_to_uf_metrics(payload, model_name=model_name, filter_dict=self.filter_dict)
 
-                results[model_name]["per_sequence"][seq_name] = self._compute(predictions, references)
+                results[model_name]["per_sequence"][seq_name] = self._compute(predictions=predictions, references=references)
 
             # overall 
             model_payload = Payload(
@@ -166,7 +164,7 @@ class UserFriendlyMetrics(evaluate.Metric):
                 )
             predictions, references = payload_to_uf_metrics(payload, model_name=model_name, filter_dict=self.filter_dict)
 
-            results[model_name]["overall"] = self._compute(predictions, references)
+            results[model_name]["overall"] = self._compute(predictions=predictions, references=references)
 
         return results
 
@@ -220,19 +218,14 @@ class UserFriendlyMetrics(evaluate.Metric):
 
         categories = {
             "user_friendly_metrics": {
-                "mostly_tracked_score_0.3",
-                "mostly_tracked_score_0.5",
-                "mostly_tracked_score_0.8",
+                f"mostly_tracked_score_{str(threshold).replace('.', '_')}" for threshold in self.recognition_thresholds
             },
             "evaluation_metrics_dev": {
                 "recall",
             },
             "user_friendly_metrics_dev": {
-                "mostly_tracked_count_0.3",
-                "mostly_tracked_count_0.5",
-                "mostly_tracked_count_0.8",
-                "unique_obj_count",
-            },
+                f"mostly_tracked_count_{str(threshold).replace('.', '_')}" for threshold in self.recognition_thresholds
+            }.union("unique_object_count"),
             "predictions_summary": {
                 "tp",
                 "fn",