powered by
Applies the element-wise function:
nn_relu6(inplace = FALSE)
can optionally do the operation in-place. Default: FALSE
FALSE
Input: \((N, *)\) where * means, any number of additional dimensions
*
Output: \((N, *)\), same shape as the input
$$ \mbox{ReLU6}(x) = \min(\max(0,x), 6) $$
if (torch_is_installed()) { m <- nn_relu6() input <- torch_randn(2) output <- m(input) }
Run the code above in your browser using DataLab