gaussian_nll_loss(input, target, var, full=False, eps=1e-06, reduction='mean')[source]¶
Gaussian negative log likelihood loss.
input – expectation of the Gaussian distribution.
target – sample from the Gaussian distribution.
var – tensor of positive variance(s), one for each of the expectations in the input (heteroscedastic), or a single one (homoscedastic).
full (bool, optional) – include the constant term in the loss calculation. Default:
eps (float, optional) – value added to var, for stability. Default: 1e-6.
reduction (string, optional) – specifies the reduction to apply to the output:
'none': no reduction will be applied,
'mean': the output is the average of all batch member losses,
'sum': the output is the sum of all batch member losses. Default: