Linux / amd64
The deepstream people detection demo container contains a demo of running people detection model using DeepStream SDK on Jetson. The container supports running people detection on 4 video file input streams. The model used in this container is a Resnet-18 model which was originally in TensorFlow and was optimized for running on Jetson using TensorRT.
The container requires JetPack 4.4 Developer Preview (L4T R32.4.2)
Ensure these prerequisites are available on your system:
Jetson device running L4T r32.4.2
JetPack 4.4 Developer Preview (DP)
First, pull the container image:
sudo docker pull nvcr.io/nvidia/deepstream-peopledetection:r32.4.2
To run people detection demo container, run the following commands:
sudo xhost +si:localuser:root sudo docker run -it --rm --net=host --runtime nvidia -e DISPLAY=$DISPLAY -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream-peopledetection:r32.4.2 deepstream-test5-app -c deepstream-5.0/samples/configs/deepstream-app/sourceX_1080p_dec_infer-resnet_tracker_tiled_display_int8_hq_dla_nx.txt
Cloud native demo on Jetson showcases how Jetson is bringing cloud native methodolgoies like containarizaton to the edge. The demo is built around the example use case of AI applications for service robots and show cases people detection, pose detection, gaze detection and natural language processing all running simultaneously as containers on Jetson.
Please follow for instructions in https://github.com/NVIDIA-AI-IOT/jetson-cloudnative-demo gitlab on running People detection demo container as part of the cloud native demo.
deepstream people detection demo container includes various software packages with their respective licenses included within the container.
If you have any questions or need help, please visit the Jetson Developer Forums.