Hi thanks for your work
May I know how to implement with YOLOX instead of YOLOv8. I found it's slightly different between input and output, I couldn't figure out how to use data from onnx.run to create boxes.
let outputs: SessionOutputs = model.run(inputs!["images" => input.view()]?)?;
let output = outputs["output"]
.try_extract_tensor::<f32>()?
.t()
.into_owned();
println!("output: {:?}", output);
Hi thanks for your work May I know how to implement with YOLOX instead of YOLOv8. I found it's slightly different between input and output, I couldn't figure out how to use data from onnx.run to create boxes.