BatchNorm Members
The BatchNorm type exposes the following members.
Constructors
Name | Description | |
---|---|---|
![]() |
BatchNorm()()()() |
Initializes a new instance of the BatchNorm class.
|
![]() |
BatchNorm(Single, String, String, String, String, Boolean, Single, Single) |
Initializes a new instance of the BatchNorm class.
|
![]() |
BatchNorm(Int32, Single, String, String, String, String, Boolean, Single, Single) |
Initializes a new instance of the BatchNorm class.
|
Methods
Name | Description | |
---|---|---|
![]() |
Equals(System.Object) | (Inherited from Object.) |
![]() |
Finalize | (Inherited from Object.) |
![]() |
GetHashCode | (Inherited from Object.) |
![]() |
GetType | (Inherited from Object.) |
![]() |
MemberwiseClone | (Inherited from Object.) |
![]() |
ToString | (Inherited from Object.) |
Properties
Name | Description | |
---|---|---|
![]() |
BetaInitializer |
Initializer for the beta weight.
|
![]() |
BlendTimeConst |
The blend time constant in samples.
|
![]() |
Epsilon |
Small float added to variance to avoid dividing by zero.
|
![]() |
GammaInitializer |
Initializer for the gamma weight.
|
![]() |
Name |
Gets or sets the name of the network layer
(Inherited from LayerConfig.) |
![]() |
NormalizationTimeConstant |
The time constant in samples of the first-order low-pass filter that is used to compute mean/variance statistics for use in inference
|
![]() |
Params |
Gets or sets the parameters.
(Inherited from LayerConfig.) |
![]() |
RunningMeanInitializer |
Initializer for the running mean weight.
|
![]() |
RunningStdInvInitializer |
Initializer for the running standard inv weight.
|
![]() |
Shape |
The input shape for batch norm layer
|
![]() |
Spatial |
Boolean, if yes the input data is spatial (2D). If not, then sets to 1D
|