Modifier and Type | Method and Description |
---|---|
BatchNorm |
build()
Builds a
BatchNorm block. |
BatchNorm.Builder |
optAxis(int axis)
Set the axis in which channel is specified.
|
BatchNorm.Builder |
optCenter(boolean val)
If True, add offset of `beta` to normalized tensor.
|
BatchNorm.Builder |
optEpsilon(float val)
Sets the epsilon value to prevent division by 0.
|
BatchNorm.Builder |
optMomentum(float val)
Set the momentum for moving average.
|
BatchNorm.Builder |
optScale(boolean val)
If True, multiply result by `gamma`.
|
public BatchNorm.Builder optAxis(int axis)
axis
- the axis in which channel is specifiedpublic BatchNorm.Builder optCenter(boolean val)
val
- True or False on whether to add and train offset valuepublic BatchNorm.Builder optScale(boolean val)
val
- True or False on whether to add and train scale valuepublic BatchNorm.Builder optEpsilon(float val)
val
- the epsilon valuepublic BatchNorm.Builder optMomentum(float val)
val
- the momentum for moving average