James Betker a930f2576e Begin a migration to specifying training rate on megasamples instead of arbitrary "steps" ... This should help me greatly in tuning models. It's also necessary now that batch size isn't really respected; we simply step once the gradient direction becomes unstable.		2022-02-09 17:25:05 -07:00
..
.idea
data	Record load times in fast_paired_dataset	2022-02-07 15:45:38 -07:00
models	ctc_code_gen: use a mean() on the ConditioningEncoder	2022-02-09 14:26:44 -07:00
scripts	script updates	2022-02-09 14:26:52 -07:00
trainer	batch_size_optimizer works. sweet! no more tuning batch sizes.	2022-02-09 14:26:23 -07:00
utils	update usage scripts	2022-01-25 17:57:26 -07:00
multi_modal_train.py
process_video.py
requirements.txt
test.py
train.py	Begin a migration to specifying training rate on megasamples instead of arbitrary "steps"	2022-02-09 17:25:05 -07:00
use_discriminator_as_filter.py