Closed Haroldhy closed 1 month ago
Thanks for your interest! Does this issue #75 help?
Thanks for your answer. The issue indicates that if I don't use the new version of tensorRT, I will need to remove the mod operator from the onnx model, then I will get a model with three outputs. 1x300x4, 1x300x1 and the output of the 1x300 shape that needs to be processed. Then just need to do a mod on the last output right?
Yes, we think so.
Please feel free to reopen this issue if you have further questions.
If you're curious about the code to do this, I have a script called v10_fixer.py here that does this
I use “yolo export model=yolov10n/s/m/b/l/x.pt format=onnx opset=13 simplify” to export onnx model. The exported model contains the fmod(Mod) operator, which is an operator supported by onnx but not by tensorRT, so when exporting the onnx model to a tensorRT model it will report an error. My target version of TensorRT is 8.4.1.