yolo11-seg engine cannot run after set batch > 1

[D-ruid]

Env

• GPU, Jetson Orin NX.
• OS, ubuntu 20.04.
• Cuda version, 11.4.315
• TensorRT version, 8.5.2.2

About this repo

• newest master branch
• run yolo11s-seg and set kBatchSize = 4 in config.h.

Your problem

I build .engine successfully, but when I run ./yolo11_seg to check the inference result, following error occur:
CUDA error 1 at /tensorrtx/yolo11/plugin/yololayer.cu:256yolo11_seg: /tensorrtx/yolo11/plugin/yololayer.cu:256: void nvinfer1::YoloLayerPlugin::forwardGpu(const float* const*, float*, cudaStream_t, int, int, int): Assertion '0' failed.
Aborted (core dumped)
Both fp16 and int8 meet this error. How can I fix it?

[mpj1234]

fix pr (#1607)

[D-ruid]

Thanks a lot!

[stale]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.