- OpenCV
- Dlib
- Numpy
- Pandas
- Run the following commands
curl http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2 --output .\data\shape_predictor_68_face_landmarks.dat.bz2
mkdir data
tar -xvzf .\data\shape_predictor_68_face_landmarks.dat.bz2 -C .\data\shape_predictor_68_face_landmarks.dat
- Download face dataset
- Download UTKFace.tar.gz from this link and move the extracted folder to data (final path:
data/UTKFace
) - Download landmark lists from this link and move the txt files to data/landmark_list.
- Check for file name errors
Label: [age]_[gender]_[race]_[date&time].jpg
- [age] is an integer from 0 to 116, indicating the age
- [gender] is either 0 (male) or 1 (female)
- [race] is an integer from 0 to 4, denoting White, Black, Asian, Indian, and Others (like Hispanic, Latino, Middle Eastern).
- [date&time] is in the format of yyyymmddHHMMSSFFF, showing the date and time an image was collected to UTKFace
- File names should be checked and matched with landmark_list.txt