Why the g_loss becomes negative? about ssgan-tensorflow HOT 6 OPEN

Ideally, the g_loss shouldn't be negative. Can you describe the issue more accurately?

from ssgan-tensorflow.

I also get the negative g_loss when I train.

from ssgan-tensorflow.

I also get the negative g_loss when I train mnist dataset,(g_loss is always negative). I have no idea why I got the negtive g_loss

from ssgan-tensorflow.

I also get the negative g_loss when I train.

from ssgan-tensorflow.

I also get the negative g_loss when I train.

I think the g_logloss should be g_loss = tf.reduce_mean(-tf.log(1-d_fake[:, -1]+1e-7))
but not the author's provided, because the d_fake's range is [0-1] and ln(d_fake) is always negative and the weight annealing loss will be zero when the training step is 1500, but when you do the evaluation, you get a positive g_loss because the ann_weight is always 1.
Thanks!

from ssgan-tensorflow.

Ideally, the g_loss shouldn't be negative. Can you describe the issue more accurately?

In fact, the g loss will always be negative when the train_step reaches 1500[抠鼻]

from ssgan-tensorflow.