Struct MultiLabelSoftMarginLossImpl

Inheritance Relationships

Base Type

Struct Documentation

struct torch::nn::MultiLabelSoftMarginLossImpl : public torch::nn::Cloneable<MultiLabelSoftMarginLossImpl>

Creates a criterion that optimizes a multi-label one-versus-all loss based on max-entropy, between input :math:x and target :math:y of size :math:(N, C).

See to learn about the exact behavior of this module.

See the documentation for torch::nn::MultiLabelSoftMarginLossOptions class to learn what constructor arguments are supported for this module.


MultiLabelSoftMarginLoss model(MultiLabelSoftMarginLossOptions().reduction(torch::kNone).weight(weight));

Public Functions

MultiLabelSoftMarginLossImpl(const MultiLabelSoftMarginLossOptions &options_ = {})
void pretty_print(std::ostream &stream) const override

Pretty prints the MultiLabelSoftMarginLoss module into the given stream.

void reset() override

reset() must perform initialization of all members with reference semantics, most importantly parameters, buffers and submodules.

Tensor forward(const Tensor &input, const Tensor &target)

Public Members

MultiLabelSoftMarginLossOptions options

The options with which this Module was constructed.


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources