torch.nn.functional.normalize#

torch.nn.functional.normalize(input,p=2.0,dim=1,eps=1e-12,out=None)[source]#

Perform$L_p$Lp​ normalization of inputs over specified dimension.

For a tensorinput of sizes$(n_0,\mathrm{.}\mathrm{.}\mathrm{.},n_{dim},\mathrm{.}\mathrm{.}\mathrm{.},n_k)$(n0​,...,ndim​,...,nk​), each$n_{dim}$ndim​ -element vector$v$v along dimensiondim is transformed as

$$v=\frac{v}{\max (\parallel v{\parallel }_p,ϵ)}\mathrm{.}$$v=max(∥v∥p​,ϵ)v​.

With the default arguments it uses the Euclidean norm over vectors along dimension$1$1 for normalization.

Parameters

• input (Tensor) – input tensor of any shape

• p (float) – the exponent value in the norm formulation. Default: 2

• dim (int ortuple ofints) – the dimension to reduce. Default: 1

• eps (float) – small value to avoid division by zero. Default: 1e-12

• out (Tensor,optional) – the output tensor. Ifout is used, thisoperation won’t be differentiable.

Return type

Tensor