Modifications to the YOLOv9 object detection model:

The model is now dynamically downloaded to the cache directory.
Post-processing is now done using Frigate's built-in `post_process_yolo`.
Configuration in the relevant documentation has been updated.

docs/docs/configuration/object_detectors.md

@@ -1131,7 +1131,8 @@ detectors:  # required
     type: axengine  # required
 
 model:  # required
-  path: yolov9_320  # required
+  path: frigate-yolov9-tiny  # required
+  model_type: yolo-generic # required
   width: 320  # required
   height: 320  # required
   tensor_format: bgr  # required

docs/docs/frigate/hardware.md

@@ -116,7 +116,7 @@ Frigate supports multiple different detectors that work on different types of ha
 
 | Name             | AXERA AX650N/AX8850N Inference Time |
 | ---------------- | ----------------------------------- |
-| yolov9           | ~ 1.012 ms                          |
+| yolov9-tiny      | ~ 1.012 ms                          |
 
 ### Hailo-8