delta.model.unet

delta.model.unet(input_size: Tuple[int, int, int] = (256, 32, 1), final_activation: str = 'sigmoid', output_classes: int = 1) → keras.engine.training.Model

Generic U-Net declaration.

Parameters

input_sizetuple of 3 ints, optional

Dimensions of the input tensor, excluding batch size. The default is (256,32,1).

final_activationstring or function, optional

Activation function for the final 2D convolutional layer. see keras.activations The default is ‘sigmoid’.

output_classesint, optional

Number of output classes, ie dimensionality of the output space of the last 2D convolutional layer. The default is 1.

Returns

modelModel

Defined U-Net model (not compiled yet).