Regarding the model conversion to ONNX - We do it so that FastMOT is further able to convert the ONNX file to a TRT file, which will allow for faster inference times, right? Or is there any other reason why we have to convert the model to ONNX?
Thanks in advance for all your kind help and contribution.
Hello, thanks again for this amazing work!
Regarding the model conversion to ONNX - We do it so that FastMOT is further able to convert the ONNX file to a TRT file, which will allow for faster inference times, right? Or is there any other reason why we have to convert the model to ONNX?
Thanks in advance for all your kind help and contribution.