Why no 'dilation'?

[ghost]

https://github.com/pppLang/SKNet/blob/ef76d8dd87a3c12eac69169758ee90fd1e189372/sknet.py#L24

Shouldn’t it be like this? nn.Conv2d(features, features, kernel_size=3+i*2, stride=stride, padding=1+i, groups=G, dilation=1+i),

[better153]

我认为应该改为nn.Conv2d(features, features, kernel_size=3, stride=stride, padding=1+i, dilation=1+i, groups=G)，虽然与原论文中的说法一致，但是我认为这样修改后的感受野相当于7*7