torch_amax: Amax

In torch: Tensors and Neural Networks with 'GPU' Acceleration

Amax

Description

Amax

Usage

torch_amax(self, dim = list(), keepdim = FALSE)

Arguments

self	(Tensor) the input tensor.
dim	(int or tuple of ints) the dimension or dimensions to reduce.
keepdim	(bool) whether the output tensor has dim retained or not.

amax(input, dim, keepdim=FALSE, *, out=None) -> Tensor

Returns the maximum value of each slice of the input tensor in the given dimension(s) dim.

Note

The difference between max/min and amax/amin is:

• amax/amin supports reducing on multiple dimensions,

• amax/amin does not return indices,

• amax/amin evenly distributes gradient between equal values, while max(dim)/min(dim) propagates gradient only to a single index in the source tensor.

If ⁠keepdim is ⁠TRUE⁠, the output tensors are of the same size as ⁠input⁠except in the dimension(s)⁠dim⁠where they are of size 1. Otherwise,⁠dim⁠s are squeezed (see [torch_squeeze()]), resulting in the output tensors having fewer dimension than ⁠input'.

Examples

if (torch_is_installed()) {

a <- torch_randn(c(4, 4))
a
torch_amax(a, 1)
}

torch documentation built on May 29, 2024, 9:54 a.m.