Tlt-convert failed on Jetson Nano 4G

[1733208392]

I have trained a YoloV4 model then try to convert to the engine file on my Jetson Nano. The full command is

tlt-converter -k tlt-encode \
              -d 3,608,608 \
              -o BatchedNMS \
              -e trt1.engine \
              -m 2 \
              -t fp16 \
              -i nchw \
              -p Input,1x3x608x608,1x3x608x608,2x3x608x608 \
              -w 1610612736 \
              yolov4_cspdarknet19_epoch_055.etlt

The error message is like,

[INFO] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
[ERROR] ../builder/cudnnBuilderUtils.cpp (414) - Cuda Error in findFastestTactic: 98 (invalid device function)
[WARNING] GPU memory allocation error during getBestTactic: BatchedNMS_N
[ERROR] ../builder/cudnnBuilderUtils.cpp (414) - Cuda Error in findFastestTactic: 98 (invalid device function)
[WARNING] GPU memory allocation error during getBestTactic: BatchedNMS_N
[ERROR] Try increasing the workspace size with IBuilderConfig::setMaxWorkspaceSize() if using IBuilder::buildEngineWithConfig, or IBuilder::setMaxWorkspaceSize() if using IBuilder::buildCudaEngine.
[ERROR] ../builder/tacticOptimizer.cpp (1715) - TRTInternal Error in computeCosts: 0 (Could not find any implementation for node BatchedNMS_N.)
[ERROR] ../builder/tacticOptimizer.cpp (1715) - TRTInternal Error in computeCosts: 0 (Could not find any implementation for node BatchedNMS_N.)
[ERROR] Unable to create engine

[AastaLLL]

Hi,

Do you try this conversion on the Nano device?
If yes, which JetPack/TensorRT version do you use?

Thanks.

[1733208392]

Yes, I have installed tensorOSS on Jetson Nano and run in Nano. The instructions I followed is NVIDIA TAO Documentation

dpkg -l |grep tensor
ii  nvidia-container-csv-tensorrt              7.1.3.0-1+cuda10.2                               arm64        Jetpack TensorRT CSV file
ii  tensorrt                                   7.1.3.0-1+cuda10.2                               arm64        Meta package of TensorRT

[kayccc]

Issue is following at Tlt-convert for custom trained YoloV4 model failed on Jetson Nano 4G - Intelligent Video Analytics / Transfer Learning Toolkit - NVIDIA Developer Forums