Open svjan5 opened 5 years ago
Hi @svjan5 My softplus function has max(0, x) term, so it doesn’t ignore the label, I think.
In [23]: def softplus(x): return np.maximum(0, x)+np.log(1+np.exp(-np.abs(-x)))
In [35]: softplus(1)
Out[35]: 1.3132616875182228
In [36]: softplus(-1)
Out[36]: 0.31326168751822286
Since naive softplus function often occurs overflow warning, my function has this form.
Hi,
Thank you for the reply.
I was matching your HolE implementation with the original implementation from M. Nickel (scikit-kge). There is some difference in the computation of score function (yours|his). Also he doesn't include max(0,x)
while computing loss (link).
Can you please clarify?
Hi, I couldn't understand why are we ignoring label information in
hole.py
by takingnp.abs
during softplus operation defined inmath_utils.py
(link).Thanks in advance