rank loss func bug

[MLightM]

rank loss should be ''..... - tf.multiply(pre_pw_dif, gt_pw_dif) ...‘’, '-' is missing when define the loss in rank_lstm.py

[fulifeng]

Come on! Please check the difference when we calculate: pre_pw_dif and gt_pw_dif

[MLightM]

Come on! Please check the difference when we calculate: pre_pw_dif and gt_pw_dif

oh... yes, you are right, thanks!

[wjhmike95]

why do you use "mean" to reduce rank loss instead of "sum" which is from loss equation in the essay?

[ownnaruto]

Is this loss really useful？I try so many times, just find that the results without rank loss are much better!