in

High accurate tool for automatic faces detection with landmarks


High accurate tool for automatic faces detection with landmarks.

The library is based on public detectors with high accuracy (TinaFace, Retinaface, SCRFD, …) which are combined together to form an ansamle. All models predict detections, then voting algorithm performs aggregation.

  1. Install Docker
  2. Install Nvidia Docker Container Runtime
  3. Install nvidia-container-runtime: apt-get install nvidia-container-runtime
  4. Set "default-runtime" : "nvidia" in /etc/docker/daemon.json:
    {
        "default-runtime": "nvidia",
        "runtimes": {
            "nvidia": {
                "path": "nvidia-container-runtime",
                "runtimeArgs": []
            }
        }
    }
  5. Restart Docker: systemctl restart docker
  6. Install git-lfs to pull artifacts: git lfs install

🚀  Quickstart

docker can require sudo permission and it is used in run.py script. So in this case run run.py script with sudo permission or add your user to docker group.

# clone project
https://github.com/IgorHoholko/faces_detanator

# [OPTIONAL] create virtual enviroment
virtualenv venv --python=python3.7
source venv/bin/activate

# install requirements
pip install -r requirements.txt

IMPORTANT set -s here to outputs.

  1. Now create Dockerfile for your detector with defined earlier entrypoint.
  2. Add your detector to settings.yaml by the sample.
  3. Done!

GitHub

View Github


Radial Menu for FiveM,built with React

A most easily usable JSON wrapper library in Dart