nn_poisson_nll_loss: Poisson NLL loss

Description Usage Arguments Details Shape Examples

Description

Negative log likelihood loss with Poisson distribution of target. The loss can be described as:

Usage

1
2
3
4
5
6
nn_poisson_nll_loss(
  log_input = TRUE,
  full = FALSE,
  eps = 1e-08,
  reduction = "mean"
)

Arguments

log_input

(bool, optional): if TRUE the loss is computed as \exp(\mbox{input}) - \mbox{target}*\mbox{input}, if FALSE the loss is \mbox{input} - \mbox{target}*\log(\mbox{input}+\mbox{eps}).

full

(bool, optional): whether to compute full loss, i. e. to add the Stirling approximation term \mbox{target}*\log(\mbox{target}) - \mbox{target} + 0.5 * \log(2π\mbox{target}).

eps

(float, optional): Small value to avoid evaluation of \log(0) when log_input = FALSE. Default: 1e-8

reduction

(string, optional): Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean': the sum of the output will be divided by the number of elements in the output, 'sum': the output will be summed. Note: size_average and reduce are in the process of being deprecated, and in the meantime, specifying either of those two args will override reduction. Default: 'mean'

Details

\mbox{target} \sim \mathrm{Poisson}(\mbox{input}) \mbox{loss}(\mbox{input}, \mbox{target}) = \mbox{input} - \mbox{target} * \log(\mbox{input}) + \log(\mbox{target!})

The last term can be omitted or approximated with Stirling formula. The approximation is used for target values more than 1. For targets less or equal to 1 zeros are added to the loss.

Shape

Examples

1
2
3
4
5
6
7
8
if (torch_is_installed()) {
loss <- nn_poisson_nll_loss()
log_input <- torch_randn(5, 2, requires_grad=TRUE)
target <- torch_randn(5, 2)
output <- loss(log_input, target)
output$backward()

}

Example output



torch documentation built on Oct. 7, 2021, 9:22 a.m.