mindspore.mint.nn.functional.mse_loss

mindspore.mint.nn.functional.mse_loss(input, target, reduction='mean')[source]

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

For detailed information, please refer to mindspore.nn.MSELoss.

Parameters

  • input (Tensor) – Tensor of any dimension. The data type needs to be consistent with the target. It should also be broadcastable with the target.

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

  • reduction (str, optional) –

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

Returns

  • 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 input and target .

Raises

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

  • ValueError – If input and target are not broadcastable.

  • TypeError – If input and target are in different data type.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, mint
>>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
>>> labels = Tensor(np.array([[1, 1, 1], [1, 2, 2]]), mindspore.float32)
>>> output = mint.nn.functional.mse_loss(logits, labels, reduction='none')
>>> print(output)
[[0. 1. 4.]
 [0. 0. 1.]]