mindspore.mint.nn.MSELoss

class mindspore.mint.nn.MSELoss(reduction='mean')

Calculates the mean squared error between the predicted value and the label value.

For simplicity, let $x$ and $y$ be 1-dimensional Tensor with length $N$, the unreduced loss (i.e. with argument reduction set to 'none') of $x$ and $y$ is given as:

$$\ell (x,y)=L=\{l_1,\dots ,l_N{\}}^{\mathrm{\top }},\text{with}{l}_n=(x_n-y_n{)}^2.$$

where $N$ is the batch size. If reduction is not 'none', then:

$$\begin{array}{r}\ell (x,y)=\{\begin{array}{ll}\mathrm{mean}(L),& \text{if reduction}=\text{'mean';}\\ \mathrm{sum}(L),& \text{if reduction}=\text{'sum'.}\end{array}\end{array}$$

Parameters

reduction (str, optional) –

Apply specific reduction method to the output: 'none' , 'mean' , 'sum' . Default: 'mean' .

• 'none': no reduction will be applied.

• 'mean': compute and return the mean of elements in the output.

• 'sum': the output elements will be summed.

Inputs:

• logits (Tensor) - The predicted value of the input. Tensor of any dimension. The data type needs to be consistent with the labels. It should also be broadcastable with the labels.

• labels (Tensor) - The input label. Tensor of any dimension. The data type needs to be consistent with the logits. It should also be broadcastable with the logits.

Outputs:

• Tensor. If reduction is 'mean' or 'sum', the shape of output is Tensor Scalar.

• If reduction is 'none', the shape of output is the broadcasted shape of logits and labels .

Raises

• ValueError – If reduction is not one of 'mean', 'sum' or 'none'.

• ValueError – If logits and labels are not broadcastable.

• TypeError – If logits and labels are in different data type.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> from mindspore import Tensor, mint
>>> import numpy as np
>>> # Case 1: logits.shape = labels.shape = (3,)
>>> loss = mint.nn.MSELoss()
>>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
>>> labels = Tensor(np.array([1, 1, 1]), mindspore.float32)
>>> output = loss(logits, labels)
>>> print(output)
1.6666667
>>> # Case 2: logits.shape = (3,), labels.shape = (2, 3)
>>> loss = mint.nn.MSELoss(reduction='none')
>>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
>>> labels = Tensor(np.array([[1, 1, 1], [1, 2, 2]]), mindspore.float32)
>>> output = loss(logits, labels)
>>> print(output)
[[0. 1. 4.]
 [0. 0. 1.]]