Minor bug in loss logging

[kuangdai]

Line 109 in disvae/models/losses.py:

if not is_train or self.n_train_steps % self.record_loss_every == 1:

This does not work when self.record_loss_every is 1 (recording all mini-batches).

Fix:

if not is_train or (self.n_train_steps - 1) % self.record_loss_every == 0:

[YannDubs]

Ohh I somehow I missed that... Thanks, if you send a PR I'd be happy to merge it!