0

I don't know the the operating mechanism of lasagne functions. for the code below. 

class WScaleLayer(lasagne.layers.Layer):
    def __init__(self, incoming, **kwargs):
        super(WScaleLayer, self).__init__(incoming, **kwargs)
        W = incoming.W.get_value()
        scale = np.sqrt(np.mean(W ** 2))
        incoming.W.set_value(W / scale)
        self.scale = self.add_param(scale, (), name='scale', trainable=False)
        self.b = None
        if hasattr(incoming, 'b') and incoming.b is not None:
            b = incoming.b.get_value()
            self.b = self.add_param(b, b.shape, name='b', regularizable=False)
            del incoming.params[incoming.b]
            incoming.b = None
        self.nonlinearity = lasagne.nonlinearities.linear
        if hasattr(incoming, 'nonlinearity') and incoming.nonlinearity is not None:
            self.nonlinearity = incoming.nonlinearity
            incoming.nonlinearity = lasagne.nonlinearities.linear

    def get_output_for(self, v, **kwargs):
        v = v * self.scale
        if self.b is not None:
            pattern = ['x', 0] + ['x'] * (v.ndim - 2)
            v = v + self.b.dimshuffle(*pattern)
return self.nonlinearity(v)

Can you tell me whether self.scale is constant in the training process after initialization?

aL_eX
  • 1,453
  • 2
  • 15
  • 30
zhangqianhui
  • 114
  • 1
  • 1
  • 12

1 Answers1

0

I'm not a Lasagne expert, but except if you do strange things, self.scale should not change during training.

But this code is very strange. You use the initial value of your incoming weights to initialize scale. Is that really what you want?

nouiz
  • 5,071
  • 25
  • 21