Struct BinaryCrossEntropyLossConfig 

pub struct BinaryCrossEntropyLossConfig {
    pub weights: Option<Vec<f32>>,
    pub smoothing: Option<f32>,
    pub logits: bool,
}

Configuration to create a Binary Cross-entropy loss using the init function.

Fields

weights: Option<Vec<f32>>

Create weighted binary cross-entropy with a weight for each class.

The loss of a specific sample will simply be multiplied by its label weight.

smoothing: Option<f32>

Create binary cross-entropy with label smoothing according to When Does Label Smoothing Help?.

Hard labels {0, 1} will be changed to y_smoothed = y(1 - a) + a / num_classes. Alpha = 0 would be the same as default.

logits: bool

Treat the inputs as logits, applying a sigmoid activation when computing the loss.

Implementations

impl BinaryCrossEntropyLossConfig

pub fn new() -> BinaryCrossEntropyLossConfig

Create a new instance of the config.

Arguments

Optional Arguments

weights

Create weighted binary cross-entropy with a weight for each class.

The loss of a specific sample will simply be multiplied by its label weight.

• Defaults to None

smoothing

Create binary cross-entropy with label smoothing according to When Does Label Smoothing Help?.

Hard labels {0, 1} will be changed to y_smoothed = y(1 - a) + a / num_classes. Alpha = 0 would be the same as default.

• Defaults to None

Default Arguments

logits

Treat the inputs as logits, applying a sigmoid activation when computing the loss.

• Defaults to false

impl BinaryCrossEntropyLossConfig

pub fn with_logits(self, logits: bool) -> BinaryCrossEntropyLossConfig

Sets the value for the field logits.

Treat the inputs as logits, applying a sigmoid activation when computing the loss.

• Defaults to false

pub fn with_weights( self, weights: Option<Vec<f32>>, ) -> BinaryCrossEntropyLossConfig

Sets the value for the field weights.

Create weighted binary cross-entropy with a weight for each class.

The loss of a specific sample will simply be multiplied by its label weight.

• Defaults to None

pub fn with_smoothing( self, smoothing: Option<f32>, ) -> BinaryCrossEntropyLossConfig

Sets the value for the field smoothing.

Create binary cross-entropy with label smoothing according to When Does Label Smoothing Help?.

Hard labels {0, 1} will be changed to y_smoothed = y(1 - a) + a / num_classes. Alpha = 0 would be the same as default.

• Defaults to None

impl BinaryCrossEntropyLossConfig

pub fn init(&self, device: &Device) -> BinaryCrossEntropyLoss

Initialize Binary Cross-entropy loss.

Trait Implementations

impl Clone for BinaryCrossEntropyLossConfig

fn clone(&self) -> BinaryCrossEntropyLossConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Config for BinaryCrossEntropyLossConfig

fn save<P>(&self, file: P) -> Result<(), Error>

where P: AsRef<Path>,

Saves the configuration to a file.

fn load<P>(file: P) -> Result<Self, ConfigError>

where P: AsRef<Path>,

Loads the configuration from a file.

fn load_binary(data: &[u8]) -> Result<Self, ConfigError>

Loads the configuration from a binary buffer.

impl Debug for BinaryCrossEntropyLossConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for BinaryCrossEntropyLossConfig

fn deserialize<D>( deserializer: D, ) -> Result<BinaryCrossEntropyLossConfig, <D as Deserializer<'de>>::Error>

where D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for BinaryCrossEntropyLossConfig

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

Formats the value using the given formatter.

impl Serialize for BinaryCrossEntropyLossConfig

fn serialize<S>( &self, serializer: S, ) -> Result<<S as Serializer>::Ok, <S as Serializer>::Error>

where S: Serializer,

Serialize this value into the given Serde serializer.