BatchNorm1d Type
Applies Batch Normalization over a 2D or 3D input (a mini-batch of 1D inputs with optional additional channel dimension)
The mean and standard-deviation are calculated per-dimension over the mini-batches and
\(\gamma\( and \(\beta\) are learnable parameter vectors of size \(C\) (where \(C\) is the
input size). By default, the elements of \(\gamma\) are set to 1 and the elements of
\(\beta\) are set to 0. The standard-deviation is calculated via the biased estimator,
equivalent to dsharp.var(input, unbiased=False).
Also by default, during training this layer keeps running estimates of its computed mean and variance, which are then used for normalization during evaluation. The running estimates are kept with a default momentum of 0.1.
If trackRunningStats is set to False, this layer then does not keep running estimates, and batch statistics are instead used during evaluation time as well.
Constructors
| Constructor | Description |
Full Usage:
BatchNorm1d(numFeatures, ?eps, ?momentum, ?affine, ?trackRunningStats, ?reversible)
Parameters:
int
?eps : double
?momentum : Tensor
?affine : bool
?trackRunningStats : bool
?reversible : bool
Returns: BatchNorm1d
|
|
© Copyright 2021, DiffSharp Contributors.