MTCNN by pytorch
The difference from the paper is adding batch normalization after convolution.
CeleA. CelebFaces Attributes Dataset (CelebA) is a large-scale face attributes dataset with more than 200K celebrity images, each with 40 attribute annotations. The images in this dataset cover large pose variations and background clutter. CelebA has large diversities, large quantities, and rich annotations, including
10,177 number of identities,
202,599 number of face images, and
5 landmark locations, 40 binary attributes annotations per image.
The dataset can be employed as the training and test sets for the following computer vision tasks: face attribute recognition, face detection, landmark (or facial part) localization, and face editing & synthesis.
python gen_data.py
# just change the dataset(CeleA) directory to your own in code then run it
python train_pnet.py
python train_rnet.py
python train_onet.py
python webcam_demo.py
python demo.py
Output: