- 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.
input (Tensor) – expectation of underlying Poisson distribution.
target (Tensor) – random sample .
log_input (bool) – if
Truethe loss is computed as , if
Falsethen loss is . Default:
full (bool) – whether to compute full loss, i. e. to add the Stirling approximation term. Default:
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 field
size_averageis set to
False, the losses are instead summed for each minibatch. Ignored when reduce is
eps (float, optional) – Small value to avoid evaluation of when
False. Default: 1e-8
reduce (bool, optional) – Deprecated (see
reduction). By default, the losses are averaged or summed over observations for each minibatch depending on
False, returns a loss per batch element instead and ignores
reduction (str, optional) – Specifies the reduction to apply to the output:
'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:
reduceare in the process of being deprecated, and in the meantime, specifying either of those two args will override
- Return type: