Equal Linear

더 빠른 수렴을 위해서는 linear layer 에 다른 learning rate 를 적용한다.

class EqualLinear(nn.Module):
    def __init__(
        self, in_dim, out_dim, bias=True, bias_init=0, lr_mul=1, activation=None
    ):
        super().__init__()

        self.weight = nn.Parameter(torch.randn(out_dim, in_dim).div_(lr_mul))

        if bias:
            self.bias = nn.Parameter(torch.zeros(out_dim).fill_(bias_init))
        else:
            self.bias = None

        self.activation = activation

        self.scale = (1 / math.sqrt(in_dim)) * lr_mul
        self.lr_mul = lr_mul

    def forward(self, input):
        if self.activation:
            out = F.linear(input, self.weight * self.scale)
            out = fused_leaky_relu(out, self.bias * self.lr_mul)

        else:
            out = F.linear(
                input, self.weight * self.scale, bias=self.bias * self.lr_mul
            )

        return out

    def __repr__(self):
        return (
            f'{self.__class__.__name__}({self.weight.shape[1]}, {self.weight.shape[0]})'
        )