Update README about alignment with ultralytics

README.md

@@ -92,7 +92,7 @@ model = torch.hub.load('zhiqwang/yolov5-rt-stack', 'yolov5s', pretrained=True)
 
 ### Updating checkpoint from ultralytics/yolov5
 
-The module state of `yolort` has some differences comparing to `ultralytics/yolov5`. We can load ultralytics's trained model checkpoint with minor changes, and we have converted ultralytics's release [v3.1](https://github.com/ultralytics/yolov5/releases/tag/v3.1) and [v4.0](https://github.com/ultralytics/yolov5/releases/tag/v4.0). For example, if you want to convert a `yolov5s` (release 4.0) model, you can just run the following script:
+The module state of `yolort` has some differences comparing to `ultralytics/yolov5`. We can load ultralytics's trained model checkpoint with minor changes, and we have converted ultralytics's release [v3.1](https://github.com/ultralytics/yolov5/releases/tag/v3.1) and [v4.0](https://github.com/ultralytics/yolov5/releases/tag/v4.0). For example, if you want to convert a `yolov5s` (release 4.0) model, you can just run the following script. You can also see our [how-to-align-with-ultralytics-yolov5](http://github.com/zhiqwang/yolov5-rt-stack/blob/master/notebooks/how-to-align-with-ultralytics-yolov5.ipynb) notebook for more details.
 
 ```python
 from yolort.utils import update_module_state_from_ultralytics

yolort/utils/update_module_state.py

@@ -61,8 +61,9 @@ def update_module_state_from_ultralytics(
         model = torch.hub.load(f'ultralytics/yolov5:{version}', 'custom', path_or_model=custom_path_or_model)
 
     key_arch = f'{arch}_{feature_fusion_type.lower()}_{version}'
-    assert key_arch in architecture_maps, (
-        "Currently does't support your architecture, fell free to report a issue to yolort")
+    if key_arch not in architecture_maps:
+        raise ValueError("Currently does't supports this architecture, "
+                         "fell free to file an issue labeled enhancement to us")
 
     module_state_updater = ModuleStateUpdate(
         arch=architecture_maps[key_arch],