Screen(inference) gets stuck(hang) when we deploy yolo v4 using deepstream

[SeetharamNS]

I have trained a yolo v4 with custom dataset using NVIDIA TAO and now I am trying to deploy in deepstream but the moment inference starts, screen starts hanging. I am not able resolve this. Is there any solution for this?

I am using Jetson nano 4gb (Jetpack version 4.6.1) and deepstreams 6.0

[fanzh]

please refer to these yolo samples:
opt\nvidia\deepstream\deepstream\sources\objectDetector_Yolo

DeepStream SDK FAQ

DeepStream 5.0 Manual for YoloV4 The original Yolo implementation via CUDA kernel in DeepStream is based on old Yolo models (v2, v3) so it may not suit new Yolo models like YoloV4. Location: /opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo/nvdsinfer_custom_impl_Yolo/kernels.cu We are trying to embed Yolo layer into tensorRT engine while converting darknet or pytorch into engine, this is before deploying to DeepStream. This new solution would cause the old Yolo cuda kernel…

GitHub - NVIDIA-AI-IOT/yolo_deepstream: yolo model qat and deploy with...

[fanzh]

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks