some docstring and name fix

open-mmlab · Apr 30, 2021 · df21986 · df21986
1 parent 38709ff
commit df21986
Show file tree

Hide file tree

Showing 3 changed files with 24 additions and 37 deletions.
diff --git a/mmseg/core/evaluation/metrics.py b/mmseg/core/evaluation/metrics.py
@@ -153,11 +153,11 @@ def mean_iou(results,
 
      Returns:
         dict[str, float | ndarray]:
-        <aAcc> float: Overall accuracy on all images.
-        <Acc> ndarray: Per category accuracy, shape (num_classes, ).
-        <IoU> ndarray: Per category IoU, shape (num_classes, ).
+            <aAcc> float: Overall accuracy on all images.
+            <Acc> ndarray: Per category accuracy, shape (num_classes, ).
+            <IoU> ndarray: Per category IoU, shape (num_classes, ).
     """
-    mIoU_result = eval_metrics(
+    iou_result = eval_metrics(
         results=results,
         gt_seg_maps=gt_seg_maps,
         num_classes=num_classes,
@@ -166,7 +166,7 @@ def mean_iou(results,
         nan_to_num=nan_to_num,
         label_map=label_map,
         reduce_zero_label=reduce_zero_label)
-    return mIoU_result
+    return iou_result
 
 
 def mean_dice(results,
@@ -192,12 +192,12 @@ def mean_dice(results,
 
      Returns:
         dict[str, float | ndarray]: Default metrics.
-        <aAcc> float: Overall accuracy on all images.
-        <Acc> ndarray: Per category accuracy, shape (num_classes, ).
-        <Dice> ndarray: Per category dice, shape (num_classes, ).
+            <aAcc> float: Overall accuracy on all images.
+            <Acc> ndarray: Per category accuracy, shape (num_classes, ).
+            <Dice> ndarray: Per category dice, shape (num_classes, ).
     """
 
-    mDice_result = eval_metrics(
+    dice_result = eval_metrics(
         results=results,
         gt_seg_maps=gt_seg_maps,
         num_classes=num_classes,
@@ -206,7 +206,7 @@ def mean_dice(results,
         nan_to_num=nan_to_num,
         label_map=label_map,
         reduce_zero_label=reduce_zero_label)
-    return mDice_result
+    return dice_result
 
 
 def mean_fscore(results,
@@ -236,12 +236,12 @@ def mean_fscore(results,
 
      Returns:
         dict[str, float | ndarray]: Default metrics.
-         <aAcc> float: Overall accuracy on all images.
-         <Fscore> ndarray: Per category recall, shape (num_classes, ).
-         <Precision> ndarray: Per category precision, shape (num_classes, ).
-         <Recall> ndarray: Per category f-score, shape (num_classes, ).
+            <aAcc> float: Overall accuracy on all images.
+            <Fscore> ndarray: Per category recall, shape (num_classes, ).
+            <Precision> ndarray: Per category precision, shape (num_classes, ).
+            <Recall> ndarray: Per category f-score, shape (num_classes, ).
     """
-    mFscore_result = eval_metrics(
+    fscore_result = eval_metrics(
         results=results,
         gt_seg_maps=gt_seg_maps,
         num_classes=num_classes,
@@ -251,7 +251,7 @@ def mean_fscore(results,
         label_map=label_map,
         reduce_zero_label=reduce_zero_label,
         beta=beta)
-    return mFscore_result
+    return fscore_result
 
 
 def eval_metrics(results,
@@ -277,9 +277,9 @@ def eval_metrics(results,
         label_map (dict): Mapping old labels to new labels. Default: dict().
         reduce_zero_label (bool): Wether ignore zero label. Default: False.
      Returns:
-         float: Overall accuracy on all images.
-         ndarray: Per category accuracy, shape (num_classes, ).
-         ndarray: Per category evaluation metrics, shape (num_classes, ).
+        float: Overall accuracy on all images.
+        ndarray: Per category accuracy, shape (num_classes, ).
+        ndarray: Per category evaluation metrics, shape (num_classes, ).
     """
     if isinstance(metrics, str):
         metrics = [metrics]

diff --git a/mmseg/datasets/custom.py b/mmseg/datasets/custom.py
@@ -370,7 +370,10 @@ def evaluate(self,
 
         summary_table_data = PrettyTable()
         for key, val in ret_metrics_summary.items():
-            summary_table_data.add_column(key, [val])
+            if key == 'aAcc':
+                summary_table_data.add_column(key, [val])
+            else:
+                summary_table_data.add_column('m' + key, [val])
 
         print_log('per class results:', logger)
         print_log('\n' + class_table_data.get_string(), logger=logger)

diff --git a/tests/test_metrics.py b/tests/test_metrics.py
@@ -2,23 +2,7 @@
 
 from mmseg.core.evaluation import (eval_metrics, mean_dice, mean_fscore,
                                    mean_iou)
-
-
-def f_score(precision, recall, beta=1):
-    """calcuate the f-score value.
-
-    Args:
-        precision (float | torch.Tensor): The precision value.
-        recall (float | torch.Tensor): The recall value.
-        beta (int): Determines the weight of recall in the combined score.
-            Default: False.
-
-    Returns:
-        [torch.tensor]: The f-score value.
-    """
-    score = (1 + beta**2) * (precision * recall) / (
-        (beta**2 * precision) + recall)
-    return score
+from mmseg.core.evaluation.metrics import f_score
 
 
 def get_confusion_matrix(pred_label, label, num_classes, ignore_index):