https://github.com/otamajakusi/dockerfile-yolov5-jetson
Dockerfile for yolov5 inference on NVIDIA Jetson
https://github.com/otamajakusi/dockerfile-yolov5-jetson
docker jetson jetson-nano pytorch yolov5
Last synced: 5 months ago
JSON representation
Dockerfile for yolov5 inference on NVIDIA Jetson
- Host: GitHub
- URL: https://github.com/otamajakusi/dockerfile-yolov5-jetson
- Owner: otamajakusi
- License: mit
- Created: 2021-03-14T08:10:09.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2022-10-08T01:10:52.000Z (about 3 years ago)
- Last Synced: 2023-03-09T03:51:20.399Z (over 2 years ago)
- Topics: docker, jetson, jetson-nano, pytorch, yolov5
- Language: Dockerfile
- Homepage:
- Size: 16.6 KB
- Stars: 33
- Watchers: 4
- Forks: 16
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# this repository
This repository builds docker image for object detection using Yolov5 on Nvidia Jetson platform.
All operations below should be done on Jetson platform.
## build
This operation build docker image named 'yolov5'.
```bash
./build.sh
```
If the build fails, use `--no-cache` option to clean the docker build cache.
```bash
./build.sh --no-cache
```
## run
This operation detects objects with camera connected to /dev/video0.
```bash
./run.sh
```
## run with your own weights
You can use your own weights(my-weights.pt), as follows:
```bash
mkdir -p /path/to/weights
cp my-weights.pt /path/to/weights
xhost +local:
docker run -it --rm \
--runtime nvidia \
--network host \
--device /dev/video0:/dev/video0:mrw \
-e DISPLAY=$DISPLAY \
-e LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libgomp.so.1 \
-v /tmp/.X11-unix/:/tmp/.X11-unix \
-v /path/to/weights:/weights \
yolov5 python3.8 detect.py --source 0 --weights /weights/my-weights.pt
```
## CSI Camera support
CSI Camera is not supported for this docker environment.