oneflow.nn.functional.mse_loss(input, target, reduction='mean')Tensor

This operator computes the mean squared error (squared L2 norm) loss between each element in input and target.

see MSELoss for details.

  • input (Tensor) – The input Tensor.

  • target (Tensor) – The target Tensor.

  • reduction (string, optional) – Specifies the reduction to apply to the output: 'none' | 'mean' | 'sum'. 'none': no reduction will be applied, 'mean': the sum of the output will be divided by the number of elements in the output, 'sum': the output will be summed. Default: 'mean'


>>> import oneflow as flow
>>> import oneflow.nn.functional as F
>>> input = flow.randn(3, 4, requires_grad=True)
>>> target = flow.rand(3, 4, requires_grad=False)
>>> loss = F.mse_loss(input, target)
>>> loss.backward()