knoppmyth

You're welcome.

`yolo mode=export model=runs/detect/train/weights/last.pt imgsz=[192,640] simplify=true format=onnx opset=11 `

The same error is present w/ OpenCV 4.5 and 4.7. If I export with dynamic=True, this is the error I get: `cv2.error: OpenCV(4.5.5) /io/opencv/modules/dnn/src/graph_simplifier.cpp:76: error: (-212:Parsing error) Input node with...

I'm able to export with: `yolo mode=export model=runs/detect/train/weights/best.pt imgsz=[640,640] format=onnx opset=11` OpenCV 4.7 can read the resulting ONNX file. However since the format has changed, I need to adjust my...

@qtran2021 Yes, see my code at #457.

According to the documentation I've seen, the classifier only works at 224. Most classifiers I'm aware of, work at this resolution.

I've closed #457 with code (Python) I've used that works w/ both v5 and 8 ONNX exports. Hopefully this is helpful. Look at the two `if model == "yolov8":` to...

I too use a container, I mount my output directory under the "app" directory: `docker run --ipc=host -it --gpus all -v ~/Development/YOLO/datasets:/usr/src/datasets -v ~/Development/YOLO/yolov8_runs/:/usr/src/yolov8/runs -v ~/Development/YOLO/yolov8_data/:/usr/src/yolov8/data knoppmyth/yolov8:latest`

This is being worked on and should be in a release soon. #314 #251

Here is the code I've used to read both v5 and 8 ONNX output with OpenCV: ``` def detect_yolo_onnx(confidenc, image, input_width, input_height, class_list, model, model_path, model_details): INPUT_WIDTH = input_width INPUT_HEIGHT...