diff --git a/mmdet/models/detectors/base.py b/mmdet/models/detectors/base.py
index 7d0929a760b742662563e88b6a0d8d20e6a3693d..60662929450a60e456e224f012986c05357cc6b6 100644
--- a/mmdet/models/detectors/base.py
+++ b/mmdet/models/detectors/base.py
@@ -129,8 +129,8 @@ class BaseDetector(nn.Module, metaclass=ABCMeta):
         """
         Calls either forward_train or forward_test depending on whether
         return_loss=True. Note this setting will change the expected inputs.
-        When `return_loss=False`, img and img_meta are single-nested (i.e.
-        Tensor and List[dict]), and when `resturn_loss=True`, img and img_meta
+        When `return_loss=True`, img and img_meta are single-nested (i.e.
+        Tensor and List[dict]), and when `resturn_loss=False`, img and img_meta
         should be double nested (i.e.  List[Tensor], List[List[dict]]), with
         the outer list indicating test time augmentations.
         """