Currently I am working on Object Detection model. I have trained a model, want to convert to ONNX format for real time inference and deploy in the field but I am unable to determine how to convert to onnx format. I have tried converting to onnx format and detect object on new images but its detecting wrongly. However, detectron2 trained model is able to detect the same image properly and correctly.
I converted detectron2 trained model to onnx format but not detecting the same object which is detected by detectron2 trained model