ReLu6 module

Usage

nn_relu6(inplace = FALSE)

Arguments

inplace

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

Details

$$\text{ReLU6}(x)=min(max(0,x),6)$$

Shape

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

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

Examples

if (torch_is_installed()) {
m <- nn_relu6()
input <- torch_randn(2)
output <- m(input)
}