BNNSLossFunctionCategoricalCrossEntropy
Performs categorical cross entropy computation between input prediction and labels.
Declaration
var BNNSLossFunctionCategoricalCrossEntropy: BNNSLossFunction { get }Discussion
BNNSLossFunctionCategoricalCrossEntropy performs categorical cross entropy (that is, softmax activation plus a cross entropy loss) computation between input prediction and labels.
You can scale the loss with either a scalar value or weight matrix, and reduce the loss according to a reduction function.