Class: DNN::Layers::HasParamLayer

Inherits:
Layer
  • Object
show all
Defined in:
lib/dnn/core/layers.rb

Overview

This class is a superclass of all classes with learning parameters.

Direct Known Subclasses

BatchNormalization, Conv2D, Dense

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods inherited from Layer

#backward, #built?, #forward, #prev_layer, #shape, #to_hash

Constructor Details

#initialize ⇒ HasParamLayer

Returns a new instance of HasParamLayer.



51
52
53
54
55
 
# File 'lib/dnn/core/layers.rb', line 51

def initialize
  super
  @params = {}
  @grads = {}
end

Instance Attribute Details

#grads ⇒ Object (readonly)

Differential value of parameter of layer.



49
50
51
 
# File 'lib/dnn/core/layers.rb', line 49

def grads
  @grads
end

#params ⇒ Object (readonly)

The parameters of the layer.



48
49
50
 
# File 'lib/dnn/core/layers.rb', line 48

def params
  @params
end

Instance Method Details

#build(model) ⇒ Object 



57
58
59
60
 
# File 'lib/dnn/core/layers.rb', line 57

def build(model)
  super
  init_params
end

#update ⇒ Object

Update the parameters.



63
64
65
 
# File 'lib/dnn/core/layers.rb', line 63

def update
  @model.optimizer.update(self)
end