torch.var_mean#

torch.var_mean(input,dim=None,*,correction=1,keepdim=False,out=None)#

Calculates the variance and mean over the dimensions specified bydim.dim can be a single dimension, list of dimensions, orNone toreduce over all dimensions.

The variance (${\sigma }^2$σ2) is calculated as

$${\sigma }^2=\frac{1}{\max (0,N-\delta N)}\sum _{i=0}^{N-1}(x_i-\bar{x}{)}^2$$σ2=max(0, N−δN)1​i=0∑N−1​(xi​−xˉ)2

where$x$x is the sample set of elements,$\bar{x}$xˉ is thesample mean,$N$N is the number of samples and$\delta N$δN isthecorrection.

Ifkeepdim isTrue, the output tensor is of the same sizeasinput except in the dimension(s)dim where it is of size 1.Otherwise,dim is squeezed (seetorch.squeeze()), resulting in theoutput tensor having 1 (orlen(dim)) fewer dimension(s).

Parameters

• input (Tensor) – the input tensor.

• dim (int ortuple ofints,optional) – the dimension or dimensions to reduce.IfNone, all dimensions are reduced.

Keyword Arguments

• correction (int) –

  difference between the sample size and sample degrees of freedom.Defaults toBessel’s correction,correction=1.

  Changed in version 2.0:Previously this argument was calledunbiased and was a booleanwithTrue corresponding tocorrection=1 andFalse beingcorrection=0.

• keepdim (bool,optional) – whether the output tensor hasdim retained or not. Default:False.

• out (Tensor,optional) – the output tensor.

Returns

A tuple (var, mean) containing the variance and mean.

Example

>>>a=torch.tensor(...[[0.2035,1.2959,1.8101,-0.4644],...[1.5027,-0.3270,0.5905,0.6538],...[-1.5745,1.3330,-0.5596,-0.6548],...[0.1264,-0.5080,1.6420,0.1992]]...)# fmt: skip>>>torch.var_mean(a,dim=0,keepdim=True)(tensor([[1.5926, 1.0056, 1.2005, 0.3646]]), tensor([[ 0.0645,  0.4485,  0.8707, -0.0665]]))