TLT-deepstream sample app problems : I found thatFRCNN, SSD , DSSD , RetinaNet and Detectnet_v2 can run successfully, but Yolov3 can’t

Accelerated Computing Intelligent Video Analytics TAO Toolkit
21

I ran into the same issue, here are what I did to fix the issue:

  • I first reflash my Jetson AGX XAVIER to make sure whatever I installed on it is up to date, this step is optional
    Relevant system config after installation is done:
    Jetpack 4.4 (CUDA 10.2)
    TensorRT: 7.1.3
    Deepstream: 5.0

  • Follow instruction from the link shared by Morganh to build the TensorRT OSS, make sure you use release 7.0 NOT 7.1, I used 7.1 at first and YOLOV3 failed while other models (SSD , DSSD , RetinaNet) run without issue.

#back up the original file first
cd ~
mkdir libnvinfer-plugin-backups
sudo mv /usr/lib/aarch64-linux-gnu/libnvinfer_plugin.so.7.1.3 /home/[REPLACE_WITH_YOUR_USERNAME]/libnvinfer-plugin-backups/libnvinfer_plugin.so.7.1.3.bak
#replace with the .so file built in previous step
sudo cp /home/minh/TensorRT/build/out/libnvinfer_plugin.so.7.0.0 /usr/lib/aarch64-linux-gnu/libnvinfer_plugin.so.7.1.3
sudo ldconfig
#check
ll -sh /usr/lib/aarch64-linux-gnu/libnvinfer_plugin*
make sure in the printed ouput you get the same ouput as what Morganh showed, pay close attention to the modification date, the 2 original symlinks (libnvinfer_plugin.so & libnvinfer_plugin.so.7) & the libnvinfer_plugin_static.a file should still shown Jun while the two new file (libnvinfer_plugin.so.7.0.0 & libnvinfer_plugin.so.7.1.3), for me shown Sep

I can then run the Yolov3 example without error.

2 Likes