mindspore.nn.NLLLoss

class mindspore.nn.NLLLoss(weight=None, ignore_index=- 100, reduction='mean')

Gets the negative log likelihood loss between logits and labels.

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 logits, $t$ is the labels, $w$ 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

• weight (Tensor) – The rescaling weight to each class. If the value is not None, the shape is $(C,)$. The data type only supports float32 or float16. Default: None.

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

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

Inputs:

• logits (Tensor) - Tensor of shape $(N,C)$ or $(N,C,d_1,d_2,...,d_K)$ for $K$-dimensional data, where C = number of classes. Data type must be float16 or float32. inputs needs to be logarithmic probability.

• labels (Tensor) -$(N)$ or $(N,d_1,d_2,...,d_K)$ for $K$-dimensional data. Data type must be int32.

Returns

Tensor, the computed negative log likelihood loss value.

Raises

• TypeError – If weight is not a Tensor.

• TypeError – If ignore_index is not an int.

• TypeError – If the data type of weight is not float16 or float32.

• ValueError – If reduction is not one of ‘none’, ‘mean’, ‘sum’.

• TypeError – If logits is not a Tensor.

• TypeError – If labels is not a Tensor.

Supported Platforms:

Ascend GPU CPU

Examples

>>> logits = mindspore.Tensor(np.random.randn(3, 5), mindspore.float32)
>>> labels = mindspore.Tensor(np.array([1, 0, 4]), mindspore.int32)
>>> loss = nn.NLLLoss()
>>> output = loss(logits, labels)