regularizers module¶
- class regularizers.L2Regularizer(reg_rate)¶
Bases:
regularizers.Regularizer
L2 regularizer.
- reg_rate¶
Regularization rate.
- Type
float
- __init__(reg_rate)¶
Constuctor.
- loss(param)¶
Computes the regulariztion loss of the parameters such as layer loss in dense due to large weights.
- grad(param)¶
Computes the gradient of the regularization term with respect to param.
- __repr__()¶
Returns the string representation of class.
- grad(param)¶
Computes the gradient of the regularization term with respect to param.
- Parameters
param (numpy.ndarray) – The parameter tensor.
- Returns
Regularization gradient with respect to param.
- Return type
numpy.ndarray
Notes
None
- loss(param)¶
Computes the regulariztion loss of the parameters such as layer loss in dense due to large weights.
- Parameters
param (numpy.ndarray) – The parameter tensor.
- Returns
Regularization loss.
- Return type
float
Notes
None