nn.py 文件源码

def __init__(self, incoming, num_units, theta=lasagne.init.Normal(0.1), b=lasagne.init.Constant(0.),
                 weight_scale=lasagne.init.Constant(1.), train_scale=False, nonlinearity=relu, **kwargs):
        super(DenseLayer, self).__init__(incoming, **kwargs)
        self.nonlinearity = (lasagne.nonlinearities.identity if nonlinearity is None else nonlinearity)
        self.num_units = num_units
        num_inputs = int(np.prod(self.input_shape[1:]))
        self.theta = self.add_param(theta, (num_inputs, num_units), name="theta")
        self.weight_scale = self.add_param(weight_scale, (num_units,), name="weight_scale", trainable=train_scale)
        self.W = self.theta * (self.weight_scale/T.sqrt(T.sum(T.square(self.theta),axis=0))).dimshuffle('x',0)
        self.b = self.add_param(b, (num_units,), name="b")