Package | Description |
---|---|
org.bytedeco.pytorch |
Modifier and Type | Class and Description |
---|---|
class |
MultiMarginLossImpl
Creates a criterion that optimizes a multi-class classification hinge
loss (margin-based loss) between input :math:
x (a 2D mini-batch Tensor )
and output :math:y (which is a 1D tensor of target class indices, :math:0
\leq y \leq \text{x.size}(1)-1 ). |
Modifier and Type | Method and Description |
---|---|
static Module |
MultiMarginLossImplCloneable.asModule(MultiMarginLossImplCloneable pointer) |
Copyright © 2024. All rights reserved.