nn_margin_ranking_loss {torch} | R Documentation |
Margin ranking loss
Description
Creates a criterion that measures the loss given
inputs ,
, two 1D mini-batch
Tensors
,
and a label 1D mini-batch tensor (containing 1 or -1).
If
then it assumed the first input should be ranked higher
(have a larger value) than the second input, and vice-versa for
.
Usage
nn_margin_ranking_loss(margin = 0, reduction = "mean")
Arguments
margin |
(float, optional): Has a default value of |
reduction |
(string, optional): Specifies the reduction to apply to the output:
|
Details
The loss function for each pair of samples in the mini-batch is:
Shape
Input1:
where
N
is the batch size.Input2:
, same shape as the Input1.
Target:
, same shape as the inputs.
Output: scalar. If
reduction
is'none'
, then.
Examples
if (torch_is_installed()) {
loss <- nn_margin_ranking_loss()
input1 <- torch_randn(3, requires_grad = TRUE)
input2 <- torch_randn(3, requires_grad = TRUE)
target <- torch_randn(3)$sign()
output <- loss(input1, input2, target)
output$backward()
}