torch.pow#

torch.pow(input,exponent,*,out=None)→Tensor#

Takes the power of each element ininput withexponent andreturns a tensor with the result.

exponent can be either a singlefloat number or aTensorwith the same number of elements asinput.

Whenexponent is a scalar value, the operation applied is:

$${\text{out}}_i=x_i^{\text{exponent}}$$outi​=xiexponent​

Whenexponent is a tensor, the operation applied is:

$${\text{out}}_i=x_i^{{\text{exponent}}_i}$$outi​=xiexponenti​​

Whenexponent is a tensor, the shapes ofinputandexponent must bebroadcastable.

Parameters

• input (Tensor) – the input tensor.

• exponent (float ortensor) – the exponent value

Keyword Arguments

out (Tensor,optional) – the output tensor.

Example:

>>>a=torch.randn(4)>>>atensor([ 0.4331,  1.2475,  0.6834, -0.2791])>>>torch.pow(a,2)tensor([ 0.1875,  1.5561,  0.4670,  0.0779])>>>exp=torch.arange(1.,5.)>>>a=torch.arange(1.,5.)>>>atensor([ 1.,  2.,  3.,  4.])>>>exptensor([ 1.,  2.,  3.,  4.])>>>torch.pow(a,exp)tensor([   1.,    4.,   27.,  256.])

torch.pow(self,exponent,*,out=None)→Tensor

self is a scalarfloat value, andexponent is a tensor.The returned tensorout is of the same shape asexponent

The operation applied is:

$${\text{out}}_i={\text{self}}^{{\text{exponent}}_i}$$outi​=selfexponenti​

Parameters

• self (float) – the scalar base value for the power operation

• exponent (Tensor) – the exponent tensor

Keyword Arguments

out (Tensor,optional) – the output tensor.

Example:

>>>exp=torch.arange(1.,5.)>>>base=2>>>torch.pow(base,exp)tensor([  2.,   4.,   8.,  16.])