/Facial-Expression-Recognition

Facial-Expression-Recognition in TensorFlow. Detecting faces in video and recognize the expression(emotion).

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

amazing

Opensource deep learning framework TensorFlow is used in Facial Expression Recognition(FER). The trained models achieved 65% accuracy in fer2013. If you like this, please give me a star.

Dependencies

FER requires:

  • Python (>= 3.3)
  • TensorFlow (>= 1.1.0)install
  • OpenCV (python3-version)install

Only tested in Ubuntu and macOS Sierra. Other platforms are not sure work well. When problems meet, open an issue, I'll do my best to solve that.

Usage

demo

You will have to download the pre-trained models here. Then run the demo that Detecting the face(s) in video captured by webcamera, and recognize the expression(s) in real-time.

python3 main.py demo

And you can add --showbox option to show box of faces.

train models

You can train models by yourself. Download the fer2013 datasets in kaggle(91.97MB). Extract the data to data/fer2013 folder. Then train model.

python3 main.py train

Issues & Suggestions

If any issues and suggestions to me, you can create an issue.