Python API for bob.ip.pytorch_extractor

class bob.ip.pytorch_extractor.CNN8Extractor(model_file=None, num_classes=10575)

Bases: bob.bio.base.extractor.Extractor

The class implementing the feature extraction of CASIA-Net embeddings.

network

torch.nn.Module – The network architecture

to_tensor

torchvision.transforms – The transform from numpy.array to torch.Tensor

norm

torchvision.transforms – The transform to normalize the input

__call__(image)[source]

Extract features from an image

Parameters:image (3D numpy.ndarray (floats)) – The image to extract the features from. Its size must be 3x128x128
Returns:feature – The extracted features as a 1d array of size 320
Return type:2D numpy.ndarray (floats)
__init__(model_file=None, num_classes=10575)[source]

Init method

Parameters:
  • model_file (str) – The path of the trained network to load
  • drop_rate (float) – The number of classes.
class bob.ip.pytorch_extractor.CasiaNetExtractor(model_file=None, num_classes=10575)

Bases: bob.bio.base.extractor.Extractor

The class implementing the feature extraction of CASIA-Net embeddings.

network

torch.nn.Module – The network architecture

to_tensor

torchvision.transforms – The transform from numpy.array to torch.Tensor

norm

torchvision.transforms – The transform to normalize the input

__call__(image)[source]

Extract features from an image

Parameters:image (3D numpy.ndarray (floats)) – The image to extract the features from. Its size must be 3x128x128
Returns:feature – The extracted features as a 1d array of size 320
Return type:2D numpy.ndarray (floats)
__init__(model_file=None, num_classes=10575)[source]

Init method

Parameters:
  • model_file (str) – The path of the trained network to load
  • drop_rate (float) – The number of classes.