YOLOv7-inference-service

Getting Started

Pre-requirements

Install nvidia-driver-520(gpu, cuda-11.8), nvidia-docker and docker before installing the docker container.

• Tutorial-nvidia-driver

• Tutorial-docker

• Tutorial-nvidia-docker

Loading docker images or building image

Loading docker images

sudo chmod u+x ./docker/*.sh
sudo ./docker/download.sh
docker load < yolov7-server.tar

Building image

sudo chmod u+x ./docker/*.sh
sudo ./docker/build.sh

Download yolov7

git clone https://github.com/WongKinYiu/yolov7.git

Run docker container

sudo chmod u+x ./docker/*.sh
sudo ./docker/run.sh

Run webAPI service

python3 server.py -p 550

• p: The port number of server.

Testing

python3 client.py -p <folder/files>

• p: The path of inference images. you can input the folder path or the image path.

Reference

• YOLOv7
  • https://github.com/WongKinYiu/yolov7