nmaac
Results
6
comments of
nmaac
aconc和swish速度基本一样，如果慢可以参考hswish 把sigmoid换成hard sigmoid。另外一般不需要把relu全换掉
Hi @starsky68 @xuhao-anhe , seems the error is caused by the batch size value. If you set batch size = 1, please remove the bn layers: `beta = self.sigmoid(self.fc2(self.fc1(x.mean(dim=2, keepdims=True).mean(dim=3,...
> > Hi @starsky68 @xuhao-anhe , seems the error is caused by the batch size value. If you set batch size = 1, please remove the bn layers: > >...
看样子没什么问题，你的relu baseline是正常的map吗？不用预训练直接train from scratch呢？
@Zhou-boyi1997 hello我们这边没有VGG的模型，小模型可以参考使用ShuffleNetV2
暂时没有