Struct CrossEntropyLoss 

pub struct CrossEntropyLoss {
    pub output_logits: bool,
    pub target_logits: bool,
}

Calculate the cross-entropy loss from the output logits and the targets.

Unlike the full CrossEntropyLoss, this variant accepts floating-point targets (e.g. one-hot, soft label distributions, or un-normalized logits) rather than integer class indices, and omits padding, per-class weights, and label smoothing.

Should be created using CrossEntropyLossConfig.

Fields

output_logits: bool

Treat the outputs as logits.

target_logits: bool

Treat the targets as logits.

Implementations

impl CrossEntropyLoss

pub fn forward<B: Backend>( &self, logits: Tensor<B, 2>, targets: Tensor<B, 2>, ) -> Tensor<B, 1>

Compute the criterion on the output tensor.

Shapes

• logits: [batch_size, num_classes]
• targets: [batch_size, num_classes]

Trait Implementations

impl<B: AutodiffBackend> AutodiffModule<B> for CrossEntropyLoss

type InnerModule = CrossEntropyLoss

Inner module without auto-differentiation.

fn valid(&self) -> Self::InnerModule

Returns the same module, but on the inner backend without auto-differentiation.

fn from_inner(module: Self::InnerModule) -> Self

Wraps an inner module back into an auto-diff module.

impl Clone for CrossEntropyLoss

fn clone(&self) -> CrossEntropyLoss

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CrossEntropyLoss

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Display for CrossEntropyLoss

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<B: Backend> Module<B> for CrossEntropyLoss

type Record = EmptyRecord

Type to save and load the module.

fn visit<V: ModuleVisitor<B>>(&self, _visitor: &mut V)

Visit each tensor parameter in the module with a visitor.

fn map<M: ModuleMapper<B>>(self, _mapper: &mut M) -> Self

Map each tensor parameter in the module with a mapper.

fn load_record(self, _record: Self::Record) -> Self

Load the module state from a record.

fn into_record(self) -> Self::Record

Convert the module into a record containing the state.

fn to_device(self, _: &B::Device) -> Self

Move the module and all of its sub-modules to the given device.

fn fork(self, _: &B::Device) -> Self

Fork the module and all of its sub-modules to the given device.

fn collect_devices(&self, devices: Devices<B>) -> Devices<B>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn devices(&self) -> Vec<<B as BackendTypes>::Device>

Return all the devices found in the underneath module tree without duplicates.

fn no_grad(self) -> Self

Each tensor in the module tree will not require grad.

fn train<AB>(self) -> Self::TrainModule

where AB: AutodiffBackend<InnerBackend = B>, Self: HasAutodiffModule<AB>,

Move the module and all of its sub-modules to the autodiff backend.

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules.

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.

impl ModuleDisplay for CrossEntropyLoss

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, _content: Content) -> Option<Content>

Custom attributes for the module.

impl ModuleDisplayDefault for CrossEntropyLoss

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.