mesh.cpn.face_rkg

README

FRLite-Go

FRLite-Go realizes lightweight Golang face recognition, gender prediction and age prediction without introducing opencv.

The underlying SDK is dlib_face_sdk, which is expanded on the basis of the GitHub project go-face, enhances the results of face recognition, and adds gender and age prediction.

Requirements

To compile FRLite-Go you need to have dlib (>= 19.10) and libjpeg development packages installed.

Ubuntu 18.10+, Debian sid

# Ubuntu
sudo apt-get install libdlib-dev libblas-dev libatlas-base-dev liblapack-dev libjpeg-turbo8-dev
# Debian
sudo apt-get install libdlib-dev libblas-dev libatlas-base-dev liblapack-dev libjpeg62-turbo-dev

macOS

brew install dlib

Models

Currently shape_predictor_5_face_landmarks.dat, mmod_human_face_detector.dat, dnn_age_predictor_v1.dat, dnn_gender_classifier_v1.dat and dlib_face_recognition_resnet_model_v1.dat are required.

Example

Example of FRLite-Go can refer to testing package.

License

FRLite-Go is licensed under Apache-2.0.