Engine file build fail

hello
i’ve been here for quite some time
i trained the yolov5 model in google colab and checked the object detection.

but,
An error occurs in the process of converting the learned “pt” file into an engine file.

i need help

-Jetson nano-
jetpack : 4.6
openCV : 4.5.4
TensorRT : 8.0.1.6
cuDNN : 8.2.1

----------1. error -----------
/Desktop/tensorrtx-master/yolov5/yolov5.cpp:63: nvinfer1::ICudaEngine* build_engine(unsigned int, nvinfer1::IBuilder*, nvinfer1::IBuilderConfig*, nvinfer1::DataType, float&, float&, std::__cxx11::string&): Assertion `upsample11’ failed.
Aborted

----------2. error ------------
Number of unused weights left: 18446744073709461292
deepstream-app: yolo.cpp:436: NvDsInferStatus Yolo::buildYoloNetwork(std::vector&, nvinfer1::INetworkDefinition&): Assertion `0’ failed.
Aborted (core dumped)
custom_yolov5n.pt (10.2 MB)

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

Hi,

It seems that you are using a customized implementation.
Would you mind also sharing the source with us?

Thanks.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.