init(featureChannelCount:mean:variance:beta:gamma:varianceEpsilon:momentum:)
Creates a batch normalization layer with the number of feature channels, tensors, variance epsilon, and momentum you specify.
Declaration
convenience init?(featureChannelCount: Int, mean: MLCTensor, variance: MLCTensor, beta: MLCTensor?, gamma: MLCTensor?, varianceEpsilon: Float, momentum: Float)Parameters
- featureChannelCount:
The number of feature channels.
- mean:
The mean tensor.
- variance:
The variance tensor.
- beta:
The beta tensor.
- gamma:
The gamma tensor.
- varianceEpsilon:
The variance epsilon you use for numerical stability.
- momentum:
The momentum value for the running mean and variance computation.