Deepstream fasterrcnn run error

mohamed.bakr · March 17, 2020, 4:16pm

I get this error when trying to run the objectrecognitionFasterRCNN model
deepstream-app: symbol lookup error: /root/deepstream_sdk_v4.0.2_x86_64/sources/objectDetector_FasterRCNN/nvdsinfer_custom_impl_fasterRCNN/libnvdsinfer_custom_impl_fasterRCNN.so: undefined symbol: ZN8nvinfer16plugin22createFasterRCNNPluginEiiifffNS_6DimsHWENS_7WeightsES2

AastaLLL · March 18, 2020, 5:57am

Hi,

A possible issue is that the TensorRT version incompatible.
Are you using TensorRT v6.0.2?

Thanks.

mohamed.bakr · March 18, 2020, 7:05am

I’m using tensorRT 6.0.1.8

AastaLLL · March 19, 2020, 3:22am

HI,

Just checked. We can run fasterRCNN sample with TensorRT-6.0.1.5 without issue.
Could you give the version a try?

TensorRT 6.0.1.5 GA for Ubuntu 1804 and CUDA 10.1 DEB local repo packages
https://developer.nvidia.com/compute/machine-learning/tensorrt/secure/6.0/GA_6.0.1.5/local_repos/nv-tensorrt-repo-ubuntu1804-cuda10.1-trt6.0.1.5-ga-20190913_1-1_amd64.deb

More, please also try to export the TensorRT library to see if helps.

export LD_LIBRARY_PATH= [deepstream-4.0_ROOT]/lib:[TensorRT-6.0.1.5_ROOT]/lib

Thanks.