DeepStream / Triton-Server / YOLOv9 / YOLOv7

I’m just sharing a Sample Triton-Server and Deepstream 6.4 build.

  1. Start Triton-Server with Yolo models trained on COCO Dataset
  1. Install custom parse lib NvDsInferYoloEfficientNMS for Gst-nvinferserver

The custom library is built and installed using the provided Makefile.

  1. Use Sample Application ds-6.4-ts-yolo-rtsp-out

To use this sample application, follow the steps below from within the container:

  python3 ds-6.4-ts-yolo-rtsp-out.py -i <input_files> -m <model> -c <codec> -b <bitrate> [--rtsp-ts]

  #example
  python3 ds-6.4-ts-yolo-rtsp-out.py  \
  -i file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4  \
  -m  yolov9-c \
  -c H264   

Arguments

  • -i, --input: Path to input file:// or rtsp:// elementary stream. Multiple input files can be provided.
  • -m, --model: Choice ['yolov7','yolov7x','yolov7-qat','yolov7x-qat','yolov9-c','yolov9-e', 'yolov9-c-qat','yolov9-e-qat'].
  • -c, --codec: RTSP Streaming Codec. Choose between H264 and H265. (Default: H264)
  • -b, --bitrate: Set the encoding bitrate. (Default: 4000000)
  • --rtsp-ts: Attach NTP timestamp from RTSP source. (Default: False)

Alternative option to Build Deepstream.

Use Docker File to Install Deepstream and Sample Apps.
Docker Build DeepStream - YOLO

1 Like

Thanks for the sharing!

1 Like