INNER CODE UNIT · Python

output_size

ematvey/hierarchical-attention-networks · bn_lstm.py:23

    def output_size(self):
        return self.num_units

    def __call__(self, x, state, scope=None):
        with tf.variable_scope(scope or type(self).__name__):
            c, h = state

            # Keep W_xh and W_hh separate here as well to reuse initialization methods
            x_size = x.get_shape().as_list()[1]
            W_xh = tf.get_variable('W_xh',
                [x_size, 4 * self.num_units],
                initializer=orthogonal_initializer())
            W_hh = tf.get_variable('W_hh',
                [self.num_units, 4 * self.num_units],
                initializer=bn_lstm_identity_initializer(0.95))
            bias = tf.get_variable('bias', [4 * self.num_units])

            # hidden = tf.matmul(x, W_xh) + tf.matmul(h, W_hh) + bias

View source record →