Caffe2 - Python API
A deep learning, cross platform ML framework
Public Member Functions | Public Attributes | List of all members
caffe2.python.regularizer.LogBarrier Class Reference
Inheritance diagram for caffe2.python.regularizer.LogBarrier:
caffe2.python.regularizer.Regularizer

Public Member Functions

def __init__ (self, reg_lambda, discount_policy="inv", discount_options=None)
 
- Public Member Functions inherited from caffe2.python.regularizer.Regularizer
def __init__ (self)
 
def __call__ (self, net, param_init_net, param, grad=None, by=None)
 

Public Attributes

 reg_lambda
 
 discount_policy
 
 discount_options
 
- Public Attributes inherited from caffe2.python.regularizer.Regularizer
 kEpsilon
 

Detailed Description

Wright, S., & Nocedal, J. (1999). Numerical optimization. Springer Science,
35(67-68), 7. Chapter 19

Definition at line 140 of file regularizer.py.

Constructor & Destructor Documentation

def caffe2.python.regularizer.LogBarrier.__init__ (   self,
  reg_lambda,
  discount_policy = "inv",
  discount_options = None 
)
discount is a positive weight that is decreasing, and here it is implemented
similar to the learning rate. It is specified by a learning rate policy and
corresponding options

Definition at line 146 of file regularizer.py.


The documentation for this class was generated from the following file: