torch (version 0.9.0)

nn_threshold: Threshold module

Description

Thresholds each element of the input Tensor.

Usage

nn_threshold(threshold, value, inplace = FALSE)

Arguments

threshold

The value to threshold at

value

The value to replace with

inplace

can optionally do the operation in-place. Default: FALSE

Shape

• Input: $(N,\ast )$ where * means, any number of additional dimensions

• Output: $(N,\ast )$, same shape as the input

Details

Threshold is defined as: $$y=\{\begin{array}{ll}x,& \text{ if }x>\text{threshold}\\ \text{value},& \text{ otherwise }\end{array}$$

Examples

if (torch_is_installed()) {
m <- nn_threshold(0.1, 20)
input <- torch_randn(2)
output <- m(input)
}