Loss weighting

[mrgloom]

As I can see here:

Adversarial_Video_Generation/Code/g_model.py

Line 189 in 9b0d10f

self.global_loss = combined_loss(self.scale_preds_train,

Adversarial_Video_Generation/Code/loss_functions.py

Line 7 in 9b0d10f

def combined_loss(gen_frames, gt_frames, d_preds, lam_adv=1, lam_lp=1, lam_gdl=1, l_num=2, alpha=2):

there is no weighting on GDL loss, but as I understand absolute values of L2 loss and GDL loss will have large difference. Is it normal?

@dyelax

[mrgloom]

Here I also see weights for losses, but looks like they are not used:

Adversarial_Video_Generation/Code/constants.py

Line 156 in 9b0d10f

LAM_ADV = 0.05