Where is the mapping function as your paper said ?

[Johnson-yue]

But in the code

SAN/model/san.py

Lines 39 to 42 in d88b022

	self.conv_w = nn.Sequential(nn.BatchNorm2d(rel_planes * (pow(kernel_size, 2) + 1)), nn.ReLU(inplace=True),
	nn.Conv2d(rel_planes * (pow(kernel_size, 2) + 1), out_planes // share_planes, kernel_size=1, bias=False),
	nn.BatchNorm2d(out_planes // share_planes), nn.ReLU(inplace=True),
	nn.Conv2d(out_planes // share_planes, pow(kernel_size, 2) * out_planes // share_planes, kernel_size=1))

I think the self.conv_w is the mapping function but it is different from paper

code: BN -> R -> Conv -> BN -> R -> Conv
paper: L -> R -> L

is the better performance by this code than paper format ？