

Cut VGG19

class Cut_VGG19

Class object that fetches keras' VGG19 model trained on the imagenet dataset and declares as output layers. Used as feature extractor for the perceptual loss function.

Args

• layers_to_extract: list of layers to be declared as output layers.

• patch_size: integer, defines the size of the input (patch_size x patch_size).

Attributes

• loss_model: multi-output vgg architecture with as output layers.

__init__

def __init__(patch_size, layers_to_extract)