nn.py 文件源码

def __init__(self, incoming, b=lasagne.init.Constant(0.), g=lasagne.init.Constant(1.),
                 W=lasagne.init.Normal(0.05), train_g=False, init_stdv=1., nonlinearity=relu, **kwargs):
        super(WeightNormLayer, self).__init__(incoming, **kwargs)
        self.nonlinearity = nonlinearity
        self.init_stdv = init_stdv
        k = self.input_shape[1]
        if b is not None:
            self.b = self.add_param(b, (k,), name="b", regularizable=False)
        if g is not None:
            self.g = self.add_param(g, (k,), name="g", regularizable=False, trainable=train_g)
        if len(self.input_shape)==4:
            self.axes_to_sum = (0,2,3)
            self.dimshuffle_args = ['x',0,'x','x']
        else:
            self.axes_to_sum = 0
            self.dimshuffle_args = ['x',0]

        # scale weights in layer below
        incoming.W_param = incoming.W
        #incoming.W_param.set_value(W.sample(incoming.W_param.get_value().shape))
        if incoming.W_param.ndim==4:
            if isinstance(incoming, Deconv2DLayer):
                W_axes_to_sum = (0,2,3)
                W_dimshuffle_args = ['x',0,'x','x']
            else:
                W_axes_to_sum = (1,2,3)
                W_dimshuffle_args = [0,'x','x','x']
        else:
            W_axes_to_sum = 0
            W_dimshuffle_args = ['x',0]
        if g is not None:
            incoming.W = incoming.W_param * (self.g/T.sqrt(1e-6 + T.sum(T.square(incoming.W_param),axis=W_axes_to_sum))).dimshuffle(*W_dimshuffle_args)
        else:
            incoming.W = incoming.W_param / T.sqrt(1e-6 + T.sum(T.square(incoming.W_param),axis=W_axes_to_sum,keepdims=True))