disentangled

class symm_learning.nn.disentangled.Change2DisentangledBasis(in_type: FieldType, learnable: bool = False)[source]

Changes the basis of a geometric tensor to a disentangled one.

This module applies a linear change of basis of the input escnn.nn.GeometricTensor to a disentangled/isotypic basis. In this basis the group representation

Parameters:
  • in_type (FieldType) – The type of the input GeometricTensor, specifying the representation space.

  • learnable (bool, optional) – If True, the change of basis matrix is a learnable parameter. If False, it is a fixed, pre-computed matrix. Defaults to False.

evaluate_output_shape(input_shape: tuple[int, ...]) tuple[int, ...][source]

Compute the shape the output tensor which would be generated by this module when a tensor with shape input_shape is provided as input.

Parameters:

input_shape (tuple) – shape of the input tensor

Returns:

shape of the output tensor

export()[source]

Exporting to a torch.nn.Module

extra_repr() str[source]

Return the extra representation of the module.

To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.

forward(x: GeometricTensor)[source]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.