softMaxCrossEntropy(_:labels:axis:reuctionType:name:)
Creates a softmax cross-entropy loss operation and returns the result tensor.
Declaration
func softMaxCrossEntropy(_ sourceTensor: MPSGraphTensor, labels labelsTensor: MPSGraphTensor, axis: Int, reuctionType reductionType: MPSGraphLossReductionType, name: String?) -> MPSGraphTensorParameters
- sourceTensor:
The source tensor.
- labelsTensor:
The labels tensor.
- axis:
The axis over which the operation computes the softmax reduction.
- reductionType:
The type of reduction MPSGraph uses to reduce across all other axes than
axis. See: Mpsgraphlossreductiontype. - name:
The name for the operation.
Return Value
A valid MPSGraphTensor object.
Discussion
The softmax cross-entropy operation computes:
loss = reduction( - labels*ln( softmax(source) )), where
sotfmax(source) = exp(source) / sum( exp(source) ), andthe operation performs the reduction over the axis dimension.