Normalization will not work

[zhangtemplar]

I tested it and the normalization will not working:

       for W in self.fc.parameters():
            W = F.normalize(W, p=2, dim=1)

[gregunz]

This should fix it:

for _, module in self.fc.named_modules():
    if isinstance(module, nn.Linear):
        module.weight.data = F.normalize(module.weight, p=2, dim=1)

[bnu-wangxun]

This should fix it:

for _, module in self.fc.named_modules():
    if isinstance(module, nn.Linear):
        module.weight.data = F.normalize(module.weight, p=2, dim=1)

thanks

[JisongXie]

I find this problem, too. I modify it like this:

self.fc.weight.data = F.normalize(self.fc.weight.data, p=2, dim=1)

[Charlyo]

@cvqluu can you fix it in the code? thanks

[xdn-github]

I think use weight normalize layer may be a more simlple way:
in line 35 use
self.fc = weight_norm(nn.Linear(in_features, out_features, bias=False), name='weight')
instead of
self.fc = nn.Linear(in_features, out_features, bias=False)
and delete

       for W in self.fc.parameters():
            W = F.normalize(W, p=2, dim=1)