INN.Linear

Jump to bottom

Zhang Yanbo edited this page Oct 27, 2022 · 1 revision

CLASS `INN.Linear(dim, eps=1e-8)`

Invertible version of torch.nn.Linear. Using the PLU decomposition method. For the full space linear transformation, see INN.JacobianLinear.

dim : dimension of linear inputs. The outputs will have the same dimension as the input for invertibility.
eps: Additional term for avoiding log(0).

Methods

`forward(x, log_p0=0, log_det_J=0)`

Compute the forward pass. The output will be the transformed x. If compute_p=True, logp and logdet will also returned.

`inverse(y, **args)`

Compute the inverse of y. The **args is a placeholder for consistent format.