Tensorrt yolov5 model conversion fails

[opengs]

yolov5_tensorrt.sh fails with error

./yolov5 -s yolov5s-2021-07-28.wts yolov5s-2021-07-28.engine s
Loading weights: yolov5s-2021-07-28.wts
[01/05/2022-12:18:04] [E] [TRT] 3: [network.cpp::addScale::616] Error Code 3: Internal Error (Parameter check failed at: optimizer/api/network.cpp::addScale::616, condition: shift.count > 0 ? (shift.values != nullptr) : (shift.values == nullptr)
)
yolov5: /home/scribe/test/nomeroff-net/inference/convertors/yolo2tensorrt/tensorrtx/yolov5/common.hpp:155: nvinfer1::IScaleLayer* addBatchNorm2d(nvinfer1::INetworkDefinition*, std::map<std::__cxx11::basic_string<char>, nvinfer1::Weights>&, nvinfer1::ITensor&, std::__cxx11::string, float): Assertion `scale_1' failed.
bin/yolov5_tensorrt.sh: line 63: 10890 Aborted                 (core dumped) ./yolov5 -s ${yolov5s_wts} ${yolov5s_engine} s

Nvidia Jetson Nano

[opengs]

Works on v2.5 branch