megengine.functional.nn.square_loss¶

square_loss(pred, label, reduction='mean')[源代码]¶

Calculates the mean squared error (squared L2 norm) between each element in the pred \(x\) and label \(y\).

The mean squared error can be described as:

\[\ell(x, y) = mean\left( L \right)\]

where

\[L = \{l_1,\dots,l_N\}, \quad l_n = \left( x_n - y_n \right)^2,\]

\(x\) and \(y\) are tensors of arbitrary shapes with a total of \(N\) elements each. \(N\) is the batch size.

参数

pred (Tensor) – predicted result from model.
label (Tensor) – ground truth to compare.
reduction (str) – the reduction to apply to the output: ‘none’ | ‘mean’ | ‘sum’. Default: ‘mean’

返回类型

Tensor

返回

loss value.

Shape:

pred: \((N, *)\) where \(*\) means any number of additional dimensions.
label: \((N, *)\). Same shape as pred.

实际案例

import numpy as np
import megengine as mge
import megengine.functional as F

ipt = mge.tensor(np.array([3, 3, 3, 3]).astype(np.float32))
tgt = mge.tensor(np.array([2, 8, 6, 1]).astype(np.float32))
loss = F.nn.square_loss(ipt, tgt)
print(loss.numpy())

Outputs:

9.75

megengine.functional.nn.l1_loss

megengine.functional.nn.hinge_loss