Keras Layer that implements an Attention mechanism for temporal data. Supports Masking. Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]

Attention.py

def dot_product(x, kernel):
    """
    Wrapper for dot product operation, in order to be compatible with both
    Theano and Tensorflow
    Args:
        x (): input
        kernel (): weights
    Returns:
    """
    if K.backend() == 'tensorflow':
        # todo: check that this is correct
        return K.squeeze(K.dot(x, K.expand_dims(kernel)), axis=-1)
    else:
        return K.dot(x, kernel)
    

class Attention(Layer):
    def __init__(self,
                 W_regularizer=None, b_regularizer=None,
                 W_constraint=None, b_constraint=None,
                 bias=True, **kwargs):
        """
        Keras Layer that implements an Attention mechanism for temporal data.
        Supports Masking.
        Follows the work of Raffel et al. [https://arxiv.org/abs/1512.08756]
        # Input shape
            3D tensor with shape: `(samples, steps, features)`.
        # Output shape
            2D tensor with shape: `(samples, features)`.
        :param kwargs:

        Just put it on top of an RNN Layer (GRU/LSTM/SimpleRNN) with return_sequences=True.
        The dimensions are inferred based on the output shape of the RNN.
        
        
        Note: The layer has been tested with Keras 1.x 
        
        Example:
            model.add(LSTM(64, return_sequences=True))
            model.add(Attention())
            # next add a Dense layer (for classification/regression) or whatever...
            
        """
        self.supports_masking = True
        self.init = initializations.get('glorot_uniform')

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

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

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

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

        self.W = self.add_weight((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)
        else:
            self.b = None

        self.built = True

    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):
        eij = dot_product(x, self.W)

        if self.bias:
            eij += self.b

        eij = K.tanh(eij)

        a = K.exp(eij)

        # 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 ε 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]