PyTorch

Creates a criterion that optimizes a multi-class classification hinge loss (margin-based loss) between input $x$ (a 2D mini-batch Tensor) and output $y$ (which is a 1D tensor of target class indices, $0 \le y \le \text{x}.\text{size}(1) -1$):

For each mini-batch sample, loss in terms of 1D input $x$ and output $y$ is: