【Pytorch】torch.nn.functional.normalize

本文主要是介绍【Pytorch】torch.nn.functional.normalize，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

目录

本质 

官方参考

实例

---

本质 

torch.nn.functional.normalize(input, p=2, dim=1, eps=1e-12, out=None)

本质上就是按照某个维度计算范数，p表示计算p范数（等于2就是2范数），dim计算范数的维度（这里为1，一般就是通道数那个维度）

官方参考

官方api：https://pytorch.org/docs/stable/nn.html#normalize

源码：

def normalize(input, p=2, dim=1, eps=1e-12, out=None):# type: (Tensor, float, int, float, Optional[Tensor]) -> Tensorr"""Performs :math:`L_p` normalization of inputs over specified dimension.For a tensor :attr:`input` of sizes :math:`(n_0, ..., n_{dim}, ..., n_k)`, each:math:`n_{dim}` -element vector :math:`v` along dimension :attr:`dim` is transformed as.. math::v = \frac{v}{\max(\lVert v \rVert_p, \epsilon)}.With the default arguments it uses the Euclidean norm over vectors along dimension :math:`1` for normalization.Args:input: input tensor of any shapep (float): the exponent value in the norm formulation. Default: 2dim (int): the dimension to reduce. Default: 1eps (float): small value to avoid division by zero. Default: 1e-12out (Tensor, optional): the output tensor. If :attr:`out` is used, thisoperation won't be differentiable."""if out is None:denom = input.norm(p, dim, True).clamp_min(eps).expand_as(input)ret = input / denomelse:denom = input.norm(p, dim, True).clamp_min(eps).expand_as(input)ret = torch.div(input, denom, out=out)return ret

实例

input_ = torch.randn((3, 4))
a = torch.nn.Softmax()(input_)b = torch.nn.functional.normalize(a)a的结果为：
tensor([[0.2074, 0.2850, 0.1973, 0.3103],[0.2773, 0.1442, 0.3652, 0.2132],[0.3244, 0.3206, 0.0216, 0.3334]])b的结果为：
tensor([[0.4071, 0.5595, 0.3874, 0.6092],[0.5274, 0.2743, 0.6945, 0.4054],[0.5738, 0.5671, 0.0381, 0.5896]])

b中的0.4071其实就是a中的   0.2074/根号下(0.2074*0.2074+0.285*0.285+0.1973*0.1973+0.3103*0.3103) = 0.4071

这篇关于【Pytorch】torch.nn.functional.normalize的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---