[Bug]: YOLOv5, YOLOv8 ONNX Models Not Converting with trtexec on Linux

laugh12321 / TensorRT-YOLO

🚀 你的YOLO部署神器。TensorRT Plugin、CUDA Kernel、CUDA Graphs三管齐下，享受闪电般的推理速度。| Your YOLO Deployment Powerhouse. With the synergy of TensorRT Plugins, CUDA Kernels, and CUDA Graphs, experience lightning-fast inference speeds.

https://github.com/laugh12321/TensorRT-YOLO

GNU General Public License v3.0

736 stars 83 forks source link

[Bug]: YOLOv5, YOLOv8 ONNX Models Not Converting with trtexec on Linux #4

Closed laugh12321 closed 9 months ago

laugh12321 commented 9 months ago

When attempting to convert models using trtexec on Linux, the following error is encountered:

laugh12321 commented 9 months ago

Upon further investigation, it was identified that the error during the conversion using trtexec on Linux is attributed to incomplete parameters for the EfficientNMS_TRT plugin.