GAN training from scratch too erratic

[siddu9501]

Is there a random seed that works well consistently.

During training, the loss gets stuck on either Real / Fake.
This was trained from scratch on a dataset of my own. Single Identity with about ~3 hr videos

L1: 0.003016742644831538, Sync: 0.0, Percep: 0.7017908990383148 | Fake: 0.6846120357513428, Real: 0.7016448080539703: : 2it [00:03,  1.65s/it]Starting Epoch: 19022

L1: 0.003017835319042206, Sync: 0.0, Percep: 14.170929253101349 | Fake: 0.3378826081752777, Real: 14.172042548656464: : 2it [00:03,  1.66s/it]Starting Epoch: 19023

L1: 0.003155902144499123, Sync: 0.0, Percep: 27.63102149963379 | Fake: 0.0, Real: 27.63102149963379: : 2it [00:03,  1.65s/it]Starting Epoch: 19024

L1: 0.003000790602527559, Sync: 0.0, Percep: 27.63102149963379 | Fake: 0.0, Real: 27.63102149963379: : 2it [00:03,  1.66s/it]Starting Epoch: 19025

I'hv also seen this happening once the syncnet_wt gets set to 0.03 ;

[prajwalkr]

Hello,

I see you are training on your own dataset. We suggest you train without GAN first in that case. If it works, then try with a GAN after that.

[siddu9501]

I'll try that. Thank you