Struct KLDivLoss 

pub struct KLDivLoss {
    pub log_target: bool,
}

Kullback-Leibler Divergence Loss

KL Divergence shows the difference between two probability distributions by measuring information loss

KLDivLoss =

y_{true} \cdot (\log{y_{true}} - \log{y_{pred}})
    ```
By default, the loss expects the input in the log-space.
The targets may also be provided in the log-space if `log_target` is true.

See
- [Kullback–Leibler divergence](https://en.wikipedia.org/wiki/Kullback-Leibler_divergence)

Fields

log_target: bool

Specifies whether target is the log space. Default: False.

Implementations

impl KLDivLoss

pub fn forward<const D: usize, B>( &self, predictions: Tensor<B, D>, targets: Tensor<B, D>, reduction: Reduction, ) -> Tensor<B, 1>

where B: Backend,

Compute the criterion on the input tensor.

Reduction::Auto behaves as Reduction::BatchMean,Reduction::Mean dose not align with the math definition.

Shapes

• predictions: [batch_size,num_targets]
• targets: [batch_size,num_targets]
• output: [1]

pub fn forward_no_reduction<const D: usize, B>( &self, predictions: Tensor<B, D>, targets: Tensor<B, D>, ) -> Tensor<B, D>

where B: Backend,

Compute the criterion on the input tensor without reducing.

Trait Implementations

impl<B> AutodiffModule<B> for KLDivLoss

where B: AutodiffBackend,

type InnerModule = KLDivLoss

Inner module without auto-differentiation.

fn valid(&self) -> <KLDivLoss as AutodiffModule<B>>::InnerModule

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

fn from_inner( module: <KLDivLoss as AutodiffModule<B>>::InnerModule, ) -> KLDivLoss

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

impl Clone for KLDivLoss

fn clone(&self) -> KLDivLoss

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for KLDivLoss

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

Formats the value using the given formatter.

impl Display for KLDivLoss

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

Formats the value using the given formatter.

impl<B> Module<B> for KLDivLoss

where B: Backend,

type Record = EmptyRecord

Type to save and load the module.

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

where V: ModuleVisitor<B>,

Visit each tensor parameter in the module with a visitor.

fn map<M>(self, _mapper: &mut M) -> KLDivLoss

where M: ModuleMapper<B>,

Map each tensor parameter in the module with a mapper.

fn load_record(self, _record: <KLDivLoss as Module<B>>::Record) -> KLDivLoss

Load the module state from a record.

fn into_record(self) -> <KLDivLoss as Module<B>>::Record

Convert the module into a record containing the state.

fn to_device(self, _: &<B as BackendTypes>::Device) -> KLDivLoss

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

fn fork(self, _: &<B as BackendTypes>::Device) -> KLDivLoss

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

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

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 save_file<FR, PB>( self, file_path: PB, recorder: &FR, ) -> Result<(), RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Save the module to a file using the provided file recorder.

fn load_file<FR, PB>( self, file_path: PB, recorder: &FR, device: &<B as BackendTypes>::Device, ) -> Result<Self, RecorderError>

where FR: FileRecorder<B>, PB: Into<PathBuf>,

Load the module from a file using the provided file recorder.

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

Quantize the weights of the module.

impl ModuleDisplay for KLDivLoss

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.

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

Formats the module with provided display settings.

impl ModuleDisplayDefault for KLDivLoss

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.