opensphere
opensphere copied to clipboard
Bug in implementation?
Hi @ydwen
I am trying to understand your implementation of SimPLE loss.
- In the paper, Equ 6,
but in your implementation, you put
b_theta=0.3
into the score function,and let the self.bias is learning parameter.
Is this a bug?
Originally posted by @chuong98 in https://github.com/ydwen/opensphere/issues/32#issuecomment-2073210936