Struct MultiLabelClassificationOutput 

pub struct MultiLabelClassificationOutput {
    pub loss: Tensor<1>,
    pub output: Tensor<2>,
    pub targets: Tensor<2, Int>,
}

Multi-label classification output adapted for multiple metrics.

Supported metrics:

• HammingScore
• Precision (via ConfusionStatsInput)
• Recall (via ConfusionStatsInput)
• FBetaScore (via ConfusionStatsInput)
• Loss

Fields

loss: Tensor<1>

The loss.

output: Tensor<2>

The label logits or probabilities. Shape: [batch_size, num_classes].

targets: Tensor<2, Int>

The ground truth labels. Shape: [batch_size, num_classes].

Implementations

impl MultiLabelClassificationOutput

pub fn new( loss: Tensor<1>, output: Tensor<2>, targets: Tensor<2, Int>, ) -> MultiLabelClassificationOutput

Constructs a new MultiLabelClassificationOutput.

Trait Implementations

impl Adaptor<ConfusionStatsInput> for MultiLabelClassificationOutput

fn adapt(&self) -> ConfusionStatsInput

Adapt the type to be passed to a metric.

impl Adaptor<HammingScoreInput> for MultiLabelClassificationOutput

fn adapt(&self) -> HammingScoreInput

Adapt the type to be passed to a metric.

impl Adaptor<LossInput> for MultiLabelClassificationOutput

fn adapt(&self) -> LossInput

Adapt the type to be passed to a metric.

impl ItemLazy for MultiLabelClassificationOutput

fn sync(self) -> Result<MultiLabelClassificationOutput, ExecutionError>

Sync the item.