MSELoss#

classtorch.nn.MSELoss(size_average=None,reduce=None,reduction='mean')[source]#

Creates a criterion that measures the mean squared error (squared L2 norm) betweeneach element in the input$x$x and target$y$y.

The unreduced (i.e. withreduction set to'none') loss can be described as:

$$\mathrm{\ell }(x,y)=L=\{l_1,\dots ,l_N{\}}^{\mathrm{\top }},l_n={(x_n-y_n)}^2,$$ℓ(x,y)=L={l1​,…,lN​}⊤,ln​=(xn​−yn​)2,

where$N$N is the batch size. Ifreduction is not'none'(default'mean'), then:

ℓ(x,y)={mean(L),sum(L),​if reduction=‘mean’;if reduction=‘sum’.​

$x$x and$y$y are tensors of arbitrary shapes with a totalof$N$N elements each.

The mean operation still operates over all the elements, and divides by$N$N.

The division by$N$N can be avoided if one setsreduction='sum'.

Parameters

• size_average (bool,optional) – Deprecated (seereduction). By default,the losses are averaged over each loss element in the batch. Note that forsome losses, there are multiple elements per sample. If the fieldsize_averageis set toFalse, the losses are instead summed for each minibatch. Ignoredwhenreduce isFalse. Default:True

• reduce (bool,optional) – Deprecated (seereduction). By default, thelosses are averaged or summed over observations for each minibatch dependingonsize_average. Whenreduce isFalse, returns a loss perbatch element instead and ignoressize_average. Default:True

• reduction (str,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 ofelements in the output,'sum': the output will be summed. Note:size_averageandreduce are in the process of being deprecated, and in the meantime,specifying either of those two args will overridereduction. Default:'mean'

Shape:

• Input:$(\ast )$(∗), where$\ast$∗ means any number of dimensions.

• Target:$(\ast )$(∗), same shape as the input.

Examples

>>>loss=nn.MSELoss()>>>input=torch.randn(3,5,requires_grad=True)>>>target=torch.randn(3,5)>>>output=loss(input,target)>>>output.backward()

forward(input,target)[source]#

Runs the forward pass.

Return type

Tensor