plenoptic.models.Identity

Note

This object is a torch.nn.Module. It therefore has all the methods and attributes from that class, even though they are not documented here (to avoid cluttering this page).

class plenoptic.models.Identity

Bases: Module

Simple class that just returns a copy of the image.

We use this as a “dummy model” for metrics that we don’t have the representation for. We use this as the model and then just change the objective function.

Examples

>>> import plenoptic as po
>>> identity_model = po.models.Identity()
>>> identity_model
Identity()

Methods

forward(x)

Return a copy of the tensor.

forward(x)

Return a copy of the tensor.

Parameters:

x (Tensor) – The tensor to return.

Return type:

Tensor

Returns:

x – A clone of the input tensor.

Examples

>>> import plenoptic as po
>>> identity_model = po.models.Identity()
>>> img = po.data.curie()
>>> y = identity_model.forward(img)
>>> titles = ["Input", "Output (identical)"]
>>> po.plot.imshow([img, y], title=titles)
<PyrFigure ...>

(png, hires.png, pdf)