DL-Art-School/codes
James Betker ee9b199d2b Build in capacity to revert & resume networks that encounter a NaN
I'm increasingly seeing issues where something like this can be useful. In many (most?)
cases it's just a waste of compute, though. Still, better than a cold computer for a whole
night.
2021-11-01 16:14:59 -06:00
..
.idea
data Decouple MEL from nv_tacotron_dataset 2021-10-31 15:01:38 -06:00
models Condition on full signal 2021-10-30 19:58:34 -06:00
scripts Fix two scripts 2021-10-30 17:00:06 -06:00
trainer Build in capacity to revert & resume networks that encounter a NaN 2021-11-01 16:14:59 -06:00
utils Add custom clip_grad_norm that prints out the param names in error. 2021-11-01 11:12:20 -06:00
multi_modal_train.py
process_video.py
requirements.txt Fix annoying warning and add to requirements 2021-08-11 17:32:06 -06:00
test.py Add FID evaluator for diffusion models 2021-06-14 09:14:30 -06:00
train.py Add custom clip_grad_norm that prints out the param names in error. 2021-11-01 11:12:20 -06:00
use_discriminator_as_filter.py Various mods to support better jpeg image filtering 2021-06-25 13:16:15 -06:00