onnx convert tensorrt with dynamic issue

[fenghuoxiguozu]

Search before asking

• I have searched the YOLOv5 issues and found no similar bug report.

YOLOv5 Component

No response

Bug

find same issue https://github.com/ultralytics/yolov5/issues/9764

Environment

yolov5-7.0 torch1.13+ cu116 + tensorrt8.24

Minimal Reproducible Example

onnx export success:
python export.py --weights yolov5m.pt --include onnx --dynamic --simplify --opset 12

trt convert error:
trtexec --onnx=yolov5m.onnx --minShapes=images:1x3x640x640 --optShapes=images:10x3x640x640 --maxShapes=images:10x3x640x640 --saveEngine=yolov5m.engine --fp16

Additional

No response

Are you willing to submit a PR?

• Yes I'd like to help by submitting a PR!

[pderrenger]

@fenghuoxiguozu please ensure you're using the latest YOLOv5 version, as updates may resolve your issue. For guidance on TensorRT conversion, refer to our documentation at https://docs.ultralytics.com/integrations/tensorrt/. If the problem persists, consider checking the TensorRT logs for more details.