onnx model with non square input, detect error

[SangerY]

1.pt2onnx
model = YOLO('best.pt')
success = model.export(format="onnx", dynamic=False, imgsz=(800,1408), opset=12)

2.detect
def load_detection_model():
return AutoDetectionModel.from_pretrained(
model_type='yolov8onnx',
model_path=args.model_path,
confidence_threshold=args.confidence_threshold,
category_mapping=category_mapping,
device=args.device
)

...

result = get_sliced_prediction(
img_path,
model,
slice_height=args.slice_height,
slice_width=args.slice_width,
overlap_height_ratio=args.overlap_height_ratio,
overlap_width_ratio=args.overlap_width_ratio,
)

running error:

return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Got invalid dimensions for input: images for the following indices
index: 2 Got: 1408 Expected: 800
index: 3 Got: 800 Expected: 1408
Please fix either the inputs/outputs or the model.