WongKinYiu/yolor

4.2. Modeling implicit knowledge question？

violet2422 opened this issue · 2 comments

violet2422 commented

Hello, I was looking at your interesting work recently. When I saw Section 4.2, I had some questions. How is the 3 modeling methods reflected in the code?
image
I only see the following code :)

class ImplicitA(nn.Module):
    def __init__(self, channel):
        super(ImplicitA, self).__init__()
        self.channel = channel
        self.implicit = nn.Parameter(torch.zeros(1, channel, 1, 1))
        nn.init.normal_(self.implicit, std=.02)

    def forward(self):
        return self.implicit