why multi 0.01 before sigmoid function?
YanZhang-bit opened this issue · comments
"x = torch.sigmoid(0.01*self.conv3(x))" why multi 0.01 before sigmoid function?
Codes of our paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation"
YanZhang-bit opened this issue · comments
"x = torch.sigmoid(0.01*self.conv3(x))" why multi 0.01 before sigmoid function?