sigmoidCrossEntropy(reductionType:labelSmoothing:weight:)
Creates a sigmoid cross entropy loss layer with the reduction type, label smoothing, and weight you specify.
Declaration
class func sigmoidCrossEntropy(reductionType: MLCReductionType, labelSmoothing: Float, weight: Float) -> SelfParameters
- reductionType:
The reduction operation type.
- labelSmoothing:
The value for label smoothing.
- weight:
A scalar floating-point weight value.
Return Value
A sigmoid cross entropy loss layer.
See Also
Creating Loss Layers with Scalar Weights
softmaxCrossEntropy(reductionType:labelSmoothing:classCount:weight:)categoricalCrossEntropy(reductionType:labelSmoothing:classCount:weight:)log(reductionType:epsilon:weight:)huberLoss(reductionType:delta:weight:)meanAbsoluteError(reductionType:weight:)meanSquaredError(reductionType:weight:)hingeLoss(reductionType:weight:)cosineDistance(reductionType:weight:)