/Age-Gender-Smile-Multitask-Learning

In this paper, we propose an architecture of Convolutional Neural Network (CNN) which can jointly learn representations for three tasks: smile detection, gender and age classification.

Primary LanguageJupyter Notebook

Age-Gender-Smile-Multitask-Learning

In this paper, I propose an architecture of Convolutional Neural Network (CNN) which can jointly learn representations for three tasks: smile detection, gender and age classification.

My model is based on the BKNet architecture. The method used hard parameter sharing, which to reduce the overfit of training separate task. The proposed network takes input from multiple data sources, data were flow through CNN Shared Block which learns joint representations for all tasks from all the sources of data. After the shared block, we separate network into three difference tasks. Each branch then learns task-specific features and has its own loss calculation method.

Quick start

python demo.py -i image_path      # estimate image
python demo.py -v video_path      # estimate video
python demo.py                    # video stream

Dependencies

  • python 3.7+
  • tensorflow
  • numpy
  • opencv3.x
  • MTCNN for face detection

Datasets

Firstly, I prepare the training data by merge three datasets. I try to keep the number of training data for each task equally to help have the same impact of each dataset on the model

Trainning

Run trainning.ipynb. Change your datasets folder links, training parameters in config.py.

Evaluation

Run testing.ipynb to see result on the test datasets

Result

Branch Train Test
AGE 66.06% 61.36%
GENDER 97.01% 93.58%
SMILE 99.53% 92.80%

Another version

I also build age-gender-estimation based on efficientnets. If you want, please see age-gender-estimation

Reference