Fix import instructions (#315)

docs/reference/face-detection-2d-retinaface.md

@@ -175,7 +175,7 @@ Parameters:
   The WIDER Face detection dataset is supported for training, implemented as a `DetectionDataset` subclass. This example assumes the data has been downloaded and placed in the directory referenced by `data_root`.
 
   ```python
-  from opendr.perception.object_detection_2d import YOLOv3DetectorLearner
+  from opendr.perception.object_detection_2d import RetinaFaceLearner, WiderFaceDataset
   from opendr.engine.datasets import ExternalDataset
   
   dataset = WiderFaceDataset(root=data_root, splits=['train'])
@@ -246,4 +246,4 @@ The platform compatibility evaluation is also reported below:
 #### References
 <a name="retinaface-1" href="https://arxiv.org/abs/1905.00641">[1]</a> RetinaFace: Single-stage Dense Face Localisation in the Wild,
 [arXiv](https://arxiv.org/abs/1905.00641).
- 
\ No newline at end of file
+