Yolo v3-tiny-prn custom app is failing after launch

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

I am using Jetson nano B01 Developer Kit using jet[ack 4.4 and deepstream sdk 5.0.
I keep getting this error.
deepstream-app: yolo.cpp:141: NvDsInferStatus Yolo::buildYoloNetwork(std::vector&, nvinfer1::INetworkDefinition&): Assertion `m_ConfigBlocks.at(i).at(“activation”) == “linear”’ failed.
Aborted

Things i have done :

  1. My weights and cfg files are prn and have been correctly labeled in the “infer config files.txt” file .
  2. I have installed deepstream 5.0 correctly as i have run other default apps by nvidia on it.
  3. My camera is CSI and its working.

I had not initially change the yolo.cpp file for yolov3-tiny-prn and ran the app that way.
I got the same error.
I later changed the yolo.cpp file to support yolov3-tiny-prn as pointed out by this github repo

My choice for prn weights is the fps it offers compared other yolov3 models

3

Hi @immanuel.jzv,
You can check the source code in /opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo/nvdsinfer_custom_impl_Yolo/yolo.cpp about the assertion error.
I think, it should be because the activation layer is not linear, please check the difference of your darknet config and yolov3-tiny darknet config.

Thanks!