Multilabel margin loss
Creates a criterion that optimizes a multi-class multi-classification
hinge loss (margin-based loss) between input x (a 2D mini-batch Tensor)
and output y (which is a 2D Tensor of target class indices).
For each sample in the mini-batch:
nn_multilabel_margin_loss(reduction = "mean")
reduction |
(string, optional): Specifies the reduction to apply to the output:
|
\mbox{loss}(x, y) = ∑_{ij}\frac{\max(0, 1 - (x[y[j]] - x[i]))}{\mbox{x.size}(0)}
where x \in ≤ft\{0, \; \cdots , \; \mbox{x.size}(0) - 1\right\}, \ y \in ≤ft\{0, \; \cdots , \; \mbox{y.size}(0) - 1\right\}, \ 0 ≤q y[j] ≤q \mbox{x.size}(0)-1, \ and i \neq y[j] for all i and j. y and x must have the same size.
The criterion only considers a contiguous block of non-negative targets that starts at the front. This allows for different samples to have variable amounts of target classes.
Input: (C) or (N, C) where N is the batch size and C
is the number of classes.
Target: (C) or (N, C), label targets padded by -1 ensuring same shape as the input.
Output: scalar. If reduction is 'none', then (N).
if (torch_is_installed()) {
loss <- nn_multilabel_margin_loss()
x <- torch_tensor(c(0.1, 0.2, 0.4, 0.8))$view(c(1,4))
# for target y, only consider labels 4 and 1, not after label -1
y <- torch_tensor(c(4, 1, -1, 2), dtype = torch_long())$view(c(1,4))
loss(x, y)
}Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.