Skip to content

Latest commit

History

History
24 lines (15 loc) 路 854 Bytes

README.md

File metadata and controls

24 lines (15 loc) 路 854 Bytes

Real time emotion recognition

I'm using a pre-trained model with an accuracy of 68.7% over FER 2013 dataset. Thanks to @elfadly for providing with the pre trained model. If you wish to train your own model download FER2013 from Kaggle https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data

For more insight on the opencv part check out my previous repo- meme_generator Will be adding better face detection classifiers soon

Paper

Link

Download the trained model from the links given in source/trained-model.txt and place them in the same folder

Run

python3 nnModel.py

Also try

Tensorflow Tutorial