| DeepDetect

Docker

Quickstart instructions are below, for more information on DeepDetect docker images, see https://github.com/jolibrain/deepdetect/tree/master/docker.

Installation steps:

Install the NVIDIA Container Toolkit

Pull the docker image

Run the container with:

Usage

Get info from the DeepDetect server:


curl http://localhost:8080/info

Yields something like:


{
  "status":{
    "code":200,
    "msg":"OK"
  },
  "head":{
    "method":"/info",
    "version":"0.1",
    "branch":"master",
    "commit":"c8556f0b3e7d970bcd9861b910f9eae87cfd4b0c",
    "services":[]
  }
}

Use your own model repository with DeepDetect, or follow the current examples in the DeepDetect documentation.

Docker tips

Use models from outside the container:


docker run -d -u $(id -u ${USER}):$(id -g ${USER}) -p 8080:8080 -v /path/to/models:/opt/models/ jolibrain/deepdetect_gpu

where path/to/models is the path to your local models you’d like to use with the DeepDetect container.

You are now ready to use your model repositories with DeepDetect.

Looking at DeepDetect server logs:


docker logs -f

where container name can be obtained via docker ps

Platform

Server