Skip to content

OpenVino pipeline for video face detection and emotion classification

Notifications You must be signed in to change notification settings

korney3/open_vino_face_recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Data Science pipeline

Install

conda create --name open_vino_face_recognition python=3.9
conda activate open_vino_face_recognition
pip install openvino
git clone https://github.com/openvinotoolkit/open_model_zoo.git
cd open_model_zoo
git submodule update --init --recursive
cd ..
pip install openvino-dev
cd open_model_zoo/demos/face_recognition_demo/python/
omz_downloader --list models.lst
cd ../../../..
pip install open_model_zoo/demos/common/python
pip install tensorflow
pip install flask
pip install requests
pip install pytest
pip install Flask-Cors
pip install timm

Description

Запуск

В репозитории находится код для распознавания лиц на видео, идентификации и классификации эмоций.

Для запуска обработки видео вызовите функцию из ds_pipeline.py

process_video(input_video_path)

Описание моделей

Детекция лиц

  1. Face recognition - MobileNetV2 SSD, pretrained
  2. Face identification - MobileNetV2, pretrained

Распознавание эмоций

  1. 3xVGG blocks. Trained on FER2013, Fine-tune on custom teenage dataset
  2. ConvNext. Pretrained on ImageNet1k, Fine-tune FER2013

About

OpenVino pipeline for video face detection and emotion classification

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages