zea.backend.tensorflow.models.lista

Model and constructor for unfolded convolutional ISTA

Functions

UnfoldingModel(input_dim[, activation, ...])

Unfolding Iterative Shrinking and Thresholding Model

Classes

Prox(*args, **kwargs)

Proximal layer
class zea.backend.tensorflow.models.lista.Prox(*args: Any, **kwargs: Any)[source]

Bases: Layer

Proximal layer

build(input_shape)[source]
call(inputs, *args, **kwargs)[source]

Apply the proximal operator.

Parameters:

  • inputs (Tensor) – Input tensor.

  • *args – Additional positional arguments.

  • **kwargs – Additional keyword arguments.

Returns:

Output after applying the proximal operator.

Return type:

Tensor

compute_output_shape(input_shape)[source]
zea.backend.tensorflow.models.lista.UnfoldingModel(input_dim, activation=None, folds=5, upsampling=1, P0_dim=None, P1_dim=None)[source]

Unfolding Iterative Shrinking and Thresholding Model

Parameters:

  • input_dim (tuple) – input dimensions

  • activation (str, optional) – final activation function. Defaults to None.

  • folds (int, optional) – number of folds. Defaults to 5.

  • upsampling (int, optional) – upsampling of output. Defaults to 1.

  • P0_dim (list, optional) – dimensions of conv kernels. Defaults to [1, 5].

  • P1_dim (list, optional) – dimensions of conv kernels. Defaults to [1, 5].

Returns:

unfolded LISTA model

Return type:

tf model