Skip to content
Skip to content
All examples

Legacy example · Python · Version 1.0

Yolo Object Detection

AuthorsHoloscan Team (NVIDIA)
Supported platformsx86_64, aarch64
LanguagePython
Version1.0
CompatibilityHSDK 1.0.3
Contribution levelLevel 2 · Quality code
SourceHoloHub

Legacy HoloHub application

This application comes from HoloHub and was last tested with Holoscan SDK (HSDK) 1.0.3. It runs with the HoloHub CLI, ./holohub.

This project is aiming to provide basic guidance to deploy Yolo-based model to Holoscan SDK as "Bring Your Own Model"

YOLO object detection meeting demo

Supported Platforms

The demo container environment supports x86 or arm64 platforms with a discrete GPU.

Users targeting a Jetson platform (integrated GPU) may need to install Jetson PyTorch packages in their demo environment.

Model

In this application example, we use the YOLOv8s model, which is converted to ONNX format using the repository mentioned above. Note that if you provide your own ONNX model, ensure it includes the EfficientNMS_TRT layer. You can verify it using Netron. Additionally, we employ the graph_surgeon.py script to modify the input shape. For more details on this script, refer to graph_surgeonpy.

The detailed process is documented in the CMakeLists.txt file.

Input Source

This app currently supports two input options:

  1. v4l2 compatible input device
  2. Pre-recorded video

Data

This application downloads a pre-recorded video from Pexels when the application is built. Please review the license terms from Pexels.

Run

Build and launch container. Note that this will use a v4l2 input source as default.

./holohub run yolo_model_deployment

Video Replayer Support

If you don't have a v4l2 compatible device plugged in, you can also run this application on a pre-recorded video. To launch the application using the Video Stream Replayer as the input source, run:

./holohub run yolo_model_deployment --run-args="--source replayer"

Configuration

For application configuration, please refer to the yolo_detection.yaml.

All examples