Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/kingardor/yolov8-deepstream-6-1
YOLOv8 by Ultralytics in DeepStream 6.1
https://github.com/kingardor/yolov8-deepstream-6-1
deepstream gstreamer object-detection tensorrt yolov8
Last synced: 12 days ago
JSON representation
YOLOv8 by Ultralytics in DeepStream 6.1
- Host: GitHub
- URL: https://github.com/kingardor/yolov8-deepstream-6-1
- Owner: kingardor
- License: gpl-3.0
- Created: 2023-01-11T01:29:09.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-01-23T00:57:23.000Z (over 1 year ago)
- Last Synced: 2024-05-22T07:52:00.672Z (about 1 month ago)
- Topics: deepstream, gstreamer, object-detection, tensorrt, yolov8
- Language: C++
- Homepage:
- Size: 10.5 MB
- Stars: 17
- Watchers: 1
- Forks: 3
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- awesome-yolo-object-detection - kn1ghtf1re/yolov8-deepstream-6-1 - deepstream-6-1?style=social"/> : YOLOv8 by Ultralytics in DeepStream 6.1. (Applications)
README
# NVIDIA DeepStream with Ultralytics YOLOv8
Run the latest object-detection SOTA model YOLOv8 with DeepStream!
![FPS](resources/yolov8.gif)
## Repository setup
This is a straightforward step, however, if you are new to git, I recommend glancing threw the steps.
First, install git
```sh
sudo apt install git
```Next, clone the repository
```sh
https://github.com/kn1ghtf1re/yolov8-deepstream-6-1.git
```## Download the model files
You can run the `download-models.sh` script to download `onnx` yolov8 models
```sh
cd models
chmod 0777 download-models.sh
./download-models.sh
```
## Docker image buildThis repository is tested and used with `docker`. For docker setup with `nvidia`, [click here](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html).
### 1. Build the image
```sh
cd docker/dgpudocker build . -t ds-6.1:custom-1
```### 2. Start a container
```sh
xhost +export DISPLAY=:0
docker run -it --rm --net=host --runtime nvidia -e DISPLAY=$DISPLAY -v /tmp/.X11-unix/:/tmp/.X11-unix -v /home/kn1ght/Projects/yolov8-deepstream-6-1:/app ds-6.1:custom-1
```## Running the Application
### 1. Build the application
```sh
make clean && make -j$(nproc)
```### 2. Start the application
Next, create a file called `inputsources.txt` and paste the path of videos or rtsp url.
```sh
file:///home/astr1x/Videos/sample.mp4
rtsp://admin:admin%[email protected]:554/stream
```Now, run the application by running the following command:
```sh
# For barebones
./ds-yolov8# For system76 hybrid graphics
__NV_PRIME_RENDER_OFFLOAD=1 ./ds-yolov8
```## Citations
* [ultralytics/ultralytics](https://github.com/ultralytics/ultralytics)