mindspore.ops.gaussian_nll_loss

mindspore.ops.gaussian_nll_loss(x, target, var, full=False, eps=1e-06, reduction='mean')[source]

Gaussian negative log likelihood loss.

The targets are treated as samples from Gaussian distributions with expectations and variances predicted by the neural network. For a target tensor modelled as having Gaussian distribution with a tensor of expectations x and a tensor of positive variances var the loss is:

\[\text{loss} = \frac{1}{2}\left(\log\left(\text{max}\left(\text{var}, \ \text{eps}\right)\right) + \frac{\left(\text{x} - \text{target}\right)^2} {\text{max}\left(\text{var}, \ \text{eps}\right)}\right) + \text{const.}\]

where eps is used for stability of \(log\). By default, the constant term of the loss function is omitted unless \(full=True\). If the shape of \(var\) is not the same as x (due to a homoscedastic assumption), it must either have a final dimension of 1 or have one fewer dimension (with all other sizes being the same) for correct broadcasting.

Parameters

x (Tensor) – Tensor of shape \((N, *)\) or \((*)\) where \(*\) means any number of additional dimensions.
target (Tensor) – Tensor of shape \((N, *)\) or \((*)\), same shape as the x, or same shape as the x but with one dimension equal to 1 (to allow broadcasting).
var (Tensor) – Tensor of shape \((N, *)\) or \((*)\), same shape as x, or same shape as the x but with one dimension equal to 1, or same shape as the x but with one fewer dimension (to allow for broadcasting).
full (bool, optional) – Include the constant term in the loss calculation. When \(full=True\), the constant term const. will be \(0.5 * log(2\pi)\). Default: False.
eps (float, optional) – Used to improve the stability of log function must be greater than 0. Default: 1e-6.
reduction (str, optional) – Apply specific reduction method to the output: ‘none’, ‘mean’, or ‘sum’. Default: ‘mean’.

Returns

Tensor or Tensor scalar, the computed loss depending on reduction.

Raises

TypeError – If x is not a Tensor.
TypeError – If target is not a Tensor.
TypeError – If var is not a Tensor.
TypeError – If full is not a bool.
TypeError – If eps is not a float.
ValueError – If eps is not a float within [0, inf).
ValueError – If reduction is not one of ‘none’, ‘mean’, ‘sum’.

Supported Platforms:: Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor
>>> import mindspore.ops as ops
>>> import mindspore.common.dtype as mstype
>>> arr1 = np.arange(8).reshape((4, 2))
>>> arr2 = np.array([2, 3, 1, 4, 6, 4, 4, 9]).reshape((4, 2))
>>> x = Tensor(arr1, mstype.float32)
>>> var = Tensor(np.ones((4, 1)), mstype.float32)
>>> target = Tensor(arr2, mstype.float32)
>>> output = ops.gaussian_nll_loss(x, target, var)
>>> print(output)
1.4374993

Reference:: Nix, D. A. and Weigend, A. S., “Estimating the mean and variance of the target probability distribution”, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN’94), Orlando, FL, USA, 1994, pp. 55-60 vol.1, doi: 10.1109/ICNN.1994.374138.