mindspore.ops.nll_loss

mindspore.ops.nll_loss(inputs, target, weight=None, ignore_index=- 100, reduction='mean', label_smoothing=0.0)

Gets the negative log likelihood loss between inputs and target.

The nll loss with reduction=none can be described as:

$$\ell (x,t)=L={\{l_1,\dots ,l_N\}}^{\mathrm{\top }},l_n=-w_{t_n}{x}_{n,t_n},w_c=\text{ weight }[c]\cdot \mathbb{1}\{c\ne \text{ignore\_index}\},$$

where $x$ is the inputs, $t$ is the target, $w$ is the weight, N is the batch size, $c$ belonging to $[0,C-1]$ is class index, where $C$ is the number of classes.

If reduction is not ‘none’ (default ‘mean’), then

$$\begin{array}{r}\ell (x,t)=\{\begin{array}{ll}\sum _{n=1}^N\frac{1}{\sum _{n=1}^N{w}_{tn}}{l}_n,& \text{ if reduction }=\text{ 'mean', }\\ \sum _{n=1}^N{l}_n,& \text{ if reduction }=\text{ 'sum' }\end{array}\end{array}$$

Parameters

• inputs (Tensor) – $(N,C)$ where C = number of classes or $(N,C,H,W)$ in case of 2D Loss, or $(N,C,d_1,d_2,...,d_K)$. inputs is expected to be log-probabilities, data type must be float16 or float32.

• target (Tensor) – $(N)$ or $(N,d_1,d_2,...,d_K)$ for high-dimensional loss, data type must be int32.

• weight (Tensor) – A rescaling weight applied to the loss of each batch element. If not None, the shape is $(C,)$. The data type must be float16 or float32. Default: None.

• ignore_index (int) – Specifies a target value that is ignored and does not contribute to the input gradient. Default: -100

• reduction (str) – Apply specific reduction method to the output: ‘none’, ‘mean’, or ‘sum’. Default: ‘mean’.

• label_smoothing (float) – Label smoothing values, a regularization tool used to prevent the model from overfitting when calculating Loss. The value range is [0.0, 1.0]. Default value: 0.0.

Returns

Tensor, the computed loss value.

Supported Platforms:

Ascend GPU CPU

Examples

>>> inputs = mindspore.Tensor(np.random.randn(3, 5), mindspore.float32)
>>> target = mindspore.Tensor(np.array([1, 0, 4]), mindspore.int32)
>>> output = ops.nll_loss(inputs, target)