torch.nn.functional.poisson_nll_loss¶
- torch.nn.functional.poisson_nll_loss(input, target, log_input=True, full=False, size_average=None, eps=1e-08, reduce=None, reduction='mean')[source]¶
Poisson negative log likelihood loss.
See
PoissonNLLLoss
for details.- Parameters
input (Tensor) – expectation of underlying Poisson distribution.
target (Tensor) – random sample .
log_input (bool) – if
True
the loss is computed as , ifFalse
then loss is . Default:True
full (bool) – whether to compute full loss, i. e. to add the Stirling approximation term. Default:
False
.size_average (bool, optional) – Deprecated (see
reduction
). By default, the losses are averaged over each loss element in the batch. Note that for some losses, there multiple elements per sample. If the fieldsize_average
is set toFalse
, the losses are instead summed for each minibatch. Ignored when reduce isFalse
. Default:True
eps (float, optional) – Small value to avoid evaluation of when
log_input
=False
. Default: 1e-8reduce (bool, optional) – Deprecated (see
reduction
). By default, the losses are averaged or summed over observations for each minibatch depending onsize_average
. Whenreduce
isFalse
, returns a loss per batch element instead and ignoressize_average
. Default:True
reduction (str, 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
andreduce
are in the process of being deprecated, and in the meantime, specifying either of those two args will overridereduction
. Default:'mean'
- Return type