---
title: BNNSLossFunctionSoftmaxCrossEntropy
framework: accelerate
role: symbol
role_heading: Global Variable
path: accelerate/bnnslossfunctionsoftmaxcrossentropy
---

# BNNSLossFunctionSoftmaxCrossEntropy

Softmax activation on input logits, and computation of cross-entropy loss with one-hot encoded labels.

## Declaration

```swift
var BNNSLossFunctionSoftmaxCrossEntropy: BNNSLossFunction { get }
```

## Discussion

Discussion BNNSLossFunctionSoftmaxCrossEntropy performs softmax on input logits and computes cross entropy loss with one hot encoded labels. You can smooth labels can according to smoothing factor. You can scale the loss with either a scalar value or weight matrix, and reduce the loss according to a reduction function.

## See Also

### Loss Functions

- [init(_:)](accelerate/bnnslossfunction/init(_:).md)
- [init(rawValue:)](accelerate/bnnslossfunction/init(rawvalue:).md)
- [rawValue](accelerate/bnnslossfunction/rawvalue.md)
- [BNNSLossFunctionCategoricalCrossEntropy](accelerate/bnnslossfunctioncategoricalcrossentropy.md)
- [BNNSLossFunctionCosineDistance](accelerate/bnnslossfunctioncosinedistance.md)
- [BNNSLossFunctionHinge](accelerate/bnnslossfunctionhinge.md)
- [BNNSLossFunctionHuber](accelerate/bnnslossfunctionhuber.md)
- [BNNSLossFunctionLog](accelerate/bnnslossfunctionlog.md)
- [BNNSLossFunctionMeanAbsoluteError](accelerate/bnnslossfunctionmeanabsoluteerror.md)
- [BNNSLossFunctionMeanSquareError](accelerate/bnnslossfunctionmeansquareerror.md)
- [BNNSLossFunctionSigmoidCrossEntropy](accelerate/bnnslossfunctionsigmoidcrossentropy.md)
- [BNNSLossFunctionYolo](accelerate/bnnslossfunctionyolo.md)