how to compute the loss?

[arianhosseini]

Hi, I'm working on a paper, after reading the python code, it looks like the "gradient of loss" is calculated in:
fb = 1. / (1. + exp(-dot(l1, l2b.T)))
gb = (model.neg_labels - fb) * alpha

I want to be able to get the loss of an input and not the gradient of it, is there anyway to get that? is there any function that does so?

thanks for sharing

[menshikh-iv]

Looks like resolved in #1201.