attention.py

import numpy as np
import pdb
from keras import backend as K
from keras.layers import Layer, Input, merge, Dense, LSTM, Bidirectional, GRU, SimpleRNN
from keras.layers.core import Dense, Lambda, Reshape
from keras.layers.convolutional import Convolution1D
from keras.layers.merge import concatenate, dot
from keras.models import Model
from keras import regularizers, constraints
from keras.initializers import glorot_uniform
from keras.callbacks import ModelCheckpoint

class AttentionWithContext(Layer):

    def __init__(self,
                 W_regularizer=None, u_regularizer=None, b_regularizer=None,
                 W_constraint=None, u_constraint=None, b_constraint=None,
                 bias=True, **kwargs):

        self.supports_masking = True
        #self.init = initializations.get('glorot_uniform')
        self.init = glorot_uniform()

        self.W_regularizer = regularizers.get(W_regularizer)
        self.u_regularizer = regularizers.get(u_regularizer)
        self.b_regularizer = regularizers.get(b_regularizer)

        self.W_constraint = constraints.get(W_constraint)
        self.u_constraint = constraints.get(u_constraint)
        self.b_constraint = constraints.get(b_constraint)

        self.bias = bias
        super(AttentionWithContext, self).__init__(**kwargs)

    def build(self, input_shape):
        assert len(input_shape) == 3

        self.W = self.add_weight((input_shape[-1], input_shape[-1],),
                                 initializer=self.init,
                                 name='{}_W'.format(self.name),
                                 regularizer=self.W_regularizer,
                                 constraint=self.W_constraint)
        if self.bias:
            self.b = self.add_weight((input_shape[-1],),
                                     initializer='zero',
                                     name='{}_b'.format(self.name),
                                     regularizer=self.b_regularizer,
                                     constraint=self.b_constraint)

        self.u = self.add_weight((input_shape[-1],),
                                 initializer=self.init,
                                 name='{}_u'.format(self.name),
                                 regularizer=self.u_regularizer,
                                 constraint=self.u_constraint)

        super(AttentionWithContext, self).build(input_shape)

    def compute_mask(self, input, input_mask=None):
        # do not pass the mask to the next layers
        return None

    def call(self, x, mask=None):
        uit = K.dot(x, self.W)

        if self.bias:
            uit += self.b

        uit = K.tanh(uit)
        ait = K.dot(uit, self.u)

        a = K.exp(ait)

        # apply mask after the exp. will be re-normalized next
        if mask is not None:
            # Cast the mask to floatX to avoid float64 upcasting in theano
            a *= K.cast(mask, K.floatx())

        # in some cases especially in the early stages of training the sum may be almost zero
        # and this results in NaN's. A workaround is to add a very small positive number to the sum.
        # a /= K.cast(K.sum(a, axis=1, keepdims=True), K.floatx())
        a /= K.cast(K.sum(a, axis=1, keepdims=True) + K.epsilon(), K.floatx())

        a = K.expand_dims(a)
        weighted_input = x * a
        return K.sum(weighted_input, axis=1)

    def get_output_shape_for(self, input_shape):
        return input_shape[0], input_shape[-1]
    
    def compute_output_shape(self, input_shape):
        """Shape transformation logic so Keras can infer output shape
        """
        return (input_shape[0], input_shape[-1])