# SoftplusTransform#

class pytorch_forecasting.data.encoders.SoftplusTransform(cache_size=0)[source]#

Bases: Transform

Transform via the mapping $$\text{Softplus}(x) = \log(1 + \exp(x))$$. The implementation reverts to the linear function when $$x > 20$$.

Inherited-members

Methods

 forward_shape(shape) Infers the shape of the forward computation, given the input shape. inverse_shape(shape) Infers the shapes of the inverse computation, given the output shape. Computes the log det jacobian log |dy/dx| given input and output. with_cache([cache_size])

Attributes

 bijective codomain domain event_dim inv Returns the inverse Transform of this transform. sign
log_abs_det_jacobian(x, y)[source]#

Computes the log det jacobian log |dy/dx| given input and output.