5e35bf984690a196063e3eb3fe5807b1475e7d0e,capsulelayers.py,CapsuleLayer,call,#CapsuleLayer#,94

Before Change

            self.bias = K.update(self.bias, self.bias + K.sum(inputs_hat * outputs, [0, -2, -1]))

        // Handling with no routing scenario. Prior bias will always be zero.
        if self.num_routing == 0:
            c = K.softmax(self.bias)
            c_expand = K.expand_dims(K.expand_dims(K.expand_dims(c, 2), 2), 0)
            outputs = squash(K.sum(c_expand * inputs_hat, 1, keepdims=True))

        return K.reshape(outputs, [-1, self.num_capsule, self.dim_vector])

    def compute_output_shape(self, input_shape):
        return tuple([None, self.num_capsule, self.dim_vector])

After Change

            outputs = squash(K.sum(c * inputs_hat, 1, keepdims=True))

            // last iteration needs not compute bias which will not be passed to the graph any more anyway.
            if i != self.num_routing - 1:
                self.bias += K.sum(inputs_hat * outputs, -1, keepdims=True)

        return K.reshape(outputs, [-1, self.num_capsule, self.dim_vector])

    def compute_output_shape(self, input_shape):
        return tuple([None, self.num_capsule, self.dim_vector])

Instances