Inheritance diagram for Relations:

Collaboration diagram for Relations:

Public Member Functions
def	__init__ (self, number_features, hidden_feature_shape=[30, 30, 30, 30], activation=tanh, **kwargs)

def	build (self, input_shape)

def	call (self, inputs)

def	compute_output_shape (self, input_shape)

def	get_config (self)

Public Attributes
	number_features
	Number of features. More...

	number_groups
	Number of groups in input.

	hidden_feature_shape
	shape of hidden layers used for extracting relations

	activation
	activation used for hidden layer in shared weights. More...

	group_len
	how many neurons has one comparable object

	weightvariables
	saves weights for call

	combinations
	number of relation combinations

Detailed Description

This is a class which implements Relational Layer into Keras.
Relational Layer compares every combination of two feature groups with shared weights.
Use this class as every other Layer in Keras.
Relevant Paper: https://arxiv.org/abs/1706.01427
RN(O) = f_phi(sum_phi(g_theta(o_i,o_j)))
For flexibility reason only the part g(o_i,o_j) is modelled
f_phi corresponds to a MLP net
To sum over all permutations please use GlobalAveragePooling1D from keras.

Definition at line 18 of file keras_relational.py.

Constructor & Destructor Documentation

◆ init()

def __init__	(		self,
			number_features,
			hidden_feature_shape = `[30, 30, 30, 30]`,
			activation = `tanh`,
		**	kwargs
	)

Init class.

Definition at line 30 of file keras_relational.py.

     def __init__(self, number_features, hidden_feature_shape=[30, 30, 30, 30], activation=tanh, **kwargs):
         """
         Init class.
         """
  
         self.number_features = number_features
         
         self.number_groups = 0
         
         self.hidden_feature_shape = hidden_feature_shape
         
         self.activation = activations.get(activation)
         
         self.group_len = 0
         
         self.weightvariables = []
         
         self.combinations = 0
  
         super().__init__(**kwargs)

Member Function Documentation

◆ build()

def build	(	self,
		input_shape
	)

Build all weights for Relations Layer
:param input_shape: Input shape of tensor
:return:  Nothing

Definition at line 52 of file keras_relational.py.

◆ call()

def call	(	self,
		inputs
	)

Compute Relational Layer
:param inputs: input tensor
:return: output tensor

Definition at line 79 of file keras_relational.py.

◆ compute_output_shape()

def compute_output_shape	(	self,
		input_shape
	)

Compute Output shape
:return: Output shape

Definition at line 100 of file keras_relational.py.

◆ get_config()

def get_config ( self )

Config required for saving parameters in keras model.

Definition at line 112 of file keras_relational.py.

Member Data Documentation

◆ activation

activation

activation used for hidden layer in shared weights.

For output sigmoid will always be used.

Definition at line 42 of file keras_relational.py.

◆ number_features

number_features

Number of features.

Number of different shared weights used for comparison for each relation.

Definition at line 36 of file keras_relational.py.

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

mva/scripts/basf2_mva_extensions/keras_relational.py

Public Member Functions

Public Attributes