MOE.py 文件源码

def H(self, x):
      Wg = self.Wg(x)
      noise = Variable(t.randn(*Wg.size()))
      if Wg.data.type() == 'torch.cuda.FloatTensor':
         noise = noise.cuda()
      Wn = F.softplus(self.Wn(x))
      return Wg + noise*Wn

   #Take top k from H