Implementations

Dlib models

class face_engine.models.dlib_models.HOGDetector

Dlib “Histogram Oriented Gradients” model.

Note

• bounding box sizes are equal for all detections.
• detector does not provide confidence scores for detections.

name = 'hog'

class face_engine.models.dlib_models.MMODDetector

Dlib pre-trained CNN model with “Max-Margin Object Detection” loss function.

Note

• bounding box sizes are equal for all detections.
• to run in realtime requires high-end Nvidia GPU with CUDA/cuDNN.

References:

1. http://dlib.net/python/index.html
2. https://docs.nvidia.com/deeplearning/sdk/cudnn-install/index.html
3. http://dlib.net/files/mmod_human_face_detector.dat.bz2

name = 'mmod'

class face_engine.models.dlib_models.ResNetEmbedder

Dlib pre-trained face recognition ResNet model.

Note

• face alignment pre-processing used with 5 point shape_predictor.

References:

1. http://dlib.net/python/index.html
2. http://dlib.net/files/dlib_face_recognition_resnet_model_v1.dat.bz2
3. http://dlib.net/files/shape_predictor_5_face_landmarks.dat.bz2

name = 'resnet'

Basic estimator

class face_engine.models.basic_estimator.BasicEstimator

Basic estimator model makes predictions by linear comparing each source embedding vector with each fitted embedding vectors.

Model is using python pickle module to persist estimator state. Default file name is 'basic.estimator.p'.

name = 'basic'