Parameters for the forward and backward batch normalization layers.
More...
| def __init__ |
( |
|
self, |
|
|
|
alpha = 0.01, |
|
|
|
epsilon = 0.00001, |
|
|
|
dimension = 1 |
|
) |
| |
Constructs the parameters of the batch normalization layer
- Parameters
-
| alpha | Smoothing factor that is used in population mean and population variance computations |
| epsilon | A constant added to the mini-batch variance for numerical stability |
| dimension | Index of the dimension for which the normalization is performed |
Smoothing factor that is used in population mean and population variance computations
Index of the dimension for which the normalization is performed
A constant added to the mini-batch variance for numerical stability
The documentation for this class was generated from the following file:
- algorithms/neural_networks/layers/batch_normalization/__init__.py