FBeta

pytorch_lightning/metrics/__init__.py

@@ -4,7 +4,7 @@
     Accuracy,
     Precision,
     Recall,
-    Fbeta
+    FBeta
 )
 
 from pytorch_lightning.metrics.regression import (

pytorch_lightning/metrics/classification/__init__.py

@@ -1,3 +1,3 @@
 from pytorch_lightning.metrics.classification.accuracy import Accuracy
 from pytorch_lightning.metrics.classification.precision_recall import Precision, Recall
-from pytorch_lightning.metrics.classification.f_beta import Fbeta
+from pytorch_lightning.metrics.classification.f_beta import FBeta

pytorch_lightning/metrics/classification/f_beta.py

@@ -12,7 +12,7 @@
 from pytorch_lightning.metrics.utils import METRIC_EPS
 
 
-class Fbeta(Metric):
+class FBeta(Metric):
     """
     Computes f_beta metric.
 
@@ -51,10 +51,10 @@ class Fbeta(Metric):
 
     Example:
 
-        >>> from pytorch_lightning.metrics import Fbeta
+        >>> from pytorch_lightning.metrics import FBeta
         >>> target = torch.tensor([0, 1, 2, 0, 1, 2])
         >>> preds = torch.tensor([0, 2, 1, 0, 0, 1])
-        >>> f_beta = Fbeta(num_classes=3, beta=0.5)
+        >>> f_beta = FBeta(num_classes=3, beta=0.5)
         >>> f_beta(preds, target)
         tensor(0.3333)
 

tests/metrics/classification/test_f_beta.py

@@ -6,7 +6,7 @@
 import torch
 from sklearn.metrics import fbeta_score
 
-from pytorch_lightning.metrics import Fbeta
+from pytorch_lightning.metrics import FBeta
 from tests.metrics.classification.inputs import (
     _testing_binary_prob_inputs,
     _testing_binary_inputs,
@@ -97,7 +97,7 @@ def _sk_fbeta_multidim_multiclass_prob(preds, target, average='micro', beta=1.):
             False
     )
 ])
-@pytest.mark.parametrize("metric_class, beta", [(Fbeta, 0.5), (Fbeta, 1.)])
+@pytest.mark.parametrize("metric_class, beta", [(FBeta, 0.5), (FBeta, 1.)])
 def test_fbeta(
     ddp,
     dist_sync_on_step,