Struct ContrastiveLearningConfig 

pub struct ContrastiveLearningConfig {
    pub enabled: bool,
    pub temperature: f64,
    pub negative_samples: usize,
    pub hard_negative_mining: bool,
    pub momentum: f64,
    pub queue_size: usize,
    pub projection_dim: usize,
}

Contrastive learning configuration for cross-modal learning

Fields

enabled: bool

Enable contrastive learning

temperature: f64

Temperature parameter for contrastive loss

negative_samples: usize

Number of negative samples

hard_negative_mining: bool

Enable hard negative mining

momentum: f64

Momentum coefficient for momentum contrastive learning

queue_size: usize

Queue size for momentum contrastive learning

projection_dim: usize

Projection head dimension

Implementations

impl ContrastiveLearningConfig

pub fn strong() -> Self

Create strong contrastive learning configuration

Trait Implementations

impl Clone for ContrastiveLearningConfig

fn clone(&self) -> ContrastiveLearningConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ContrastiveLearningConfig

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

Formats the value using the given formatter.

impl Default for ContrastiveLearningConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ContrastiveLearningConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ContrastiveLearningConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.