search

luissen / ESRT

MIT License
164 stars 42 forks source link

What is common.Scale(1) means? #5

Open yunfanLu opened 2 years ago

yunfanLu commented 2 years ago 
class Scale(nn.Module):
    def __init__(self, init_value=1e-3):
        super().__init__()
        self.scale = nn.Parameter(torch.FloatTensor([init_value]))

    def forward(self, input):
        return input * self.scale

When the self.scale=1, does this option does nothing? Why do we need this layer?

yunfanLu commented 2 years ago

Is the self.scale learnable parameters 𝜆𝑥 in the paper?