hasktorch-gradually-typed-0.2.0.0: experimental project for hasktorch
Safe HaskellSafe-Inferred
LanguageHaskell2010

Torch.GraduallyTyped.NN.Functional.Dropout

Synopsis

Documentation

>>> import Torch.GraduallyTyped.Prelude.List (SList (..))
>>> import Torch.GraduallyTyped

dropout Source #

Arguments

:: forall gradient layout device dataType shape generatorDevice m. (SGetDevice device, SGetGeneratorDevice generatorDevice, MonadThrow m) 
=> Double

probability of an element to be zeroed

-> Tensor gradient layout device dataType shape

input

-> Generator generatorDevice

generator

-> m (Tensor gradient layout (device <+> generatorDevice) dataType shape, Generator (device <+> generatorDevice))

output

Dropout randomly zeroes some of the elements of the input tensor with probability p using samples from a Bernoulli distribution.