Big update

docs/YOLOv8.md

@@ -18,13 +18,15 @@
 git clone https://github.com/ultralytics/ultralytics.git
 cd ultralytics
 pip3 install -r requirements.txt
+python3 setup.py install
+pip3 install onnx onnxsim onnxruntime
 ```
 
 **NOTE**: It is recommended to use Python virtualenv.
 
 #### 2. Copy conversor
 
-Copy the `gen_wts_yoloV8.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder.
+Copy the `export_yoloV8.py` file from `DeepStream-Yolo/utils` directory to the `ultralytics` folder.
 
 #### 3. Download the model
 
@@ -34,14 +36,14 @@ Download the `pt` file from [YOLOv8](https://github.com/ultralytics/assets/relea
 wget https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8s.pt
 ```
 
-**NOTE**: You can use your custom model, but it is important to keep the YOLO model reference (`yolov8_`) in you `cfg` and `weights`/`wts` filenames to generate the engine correctly.
+**NOTE**: You can use your custom model.
 
 #### 4. Convert model
 
-Generate the `cfg`, `wts` and `labels.txt` (if available) files (example for YOLOv8s)
+Generate the ONNX model file (example for YOLOv8s)
 
 ```
-python3 gen_wts_yoloV8.py -w yolov8s.pt
+python3 export_yoloV8.py -w yolov8s.pt --simplify
 ```
 
 **NOTE**: To change the inference size (defaut: 640)
@@ -67,7 +69,7 @@ or
 
 #### 5. Copy generated files
 
-Copy the generated `cfg`, `wts` and `labels.txt` (if generated), files to the `DeepStream-Yolo` folder.
+Copy the generated ONNX model file to the `DeepStream-Yolo` folder.
 
 ##
 
@@ -120,11 +122,13 @@ Edit the `config_infer_primary_yoloV8.txt` file according to your model (example
 ```
 [property]
 ...
-custom-network-config=yolov8s.cfg
-model-file=yolov8s.wts
+onnx-file=yolov8s.onnx
+model-engine-file=yolov8s.onnx_b1_gpu0_fp32.engine
 ...
 num-detected-classes=80
 ...
+parse-bbox-func-name=NvDsInferParseYolo
+...
 ```
 
 ##