DL-Art-School/codes/models
James Betker 4c85ee51a4 Converge SSG architectures into unified switching base class
Also adds attention norm histogram to logging
2020-10-08 17:23:21 -06:00
..
archs Converge SSG architectures into unified switching base class 2020-10-08 17:23:21 -06:00
experiments Add in experiments hook 2020-09-19 10:05:25 -06:00
flownet2@2e9e010c98 Integrate flownet2 into codebase, add teco visual debugs 2020-10-06 20:35:39 -06:00
layers Add ImageFlowInjector 2020-09-19 10:07:00 -06:00
steps Fix more distributed bugs 2020-10-08 14:32:45 -06:00
__init__.py ExtensibleTrainer work 2020-08-22 08:24:34 -06:00
base_model.py Move to apex distributeddataparallel and add switch all_reduce 2020-10-08 11:20:05 -06:00
ExtensibleTrainer.py Fix more distributed bugs 2020-10-08 14:32:45 -06:00
feature_model.py Feature mode -> back to LR fea 2020-09-11 13:09:55 -06:00
loss.py Update loss with lr crossgan 2020-08-26 17:57:22 -06:00
lr_scheduler.py Extensible trainer (in progress) 2020-08-12 08:45:23 -06:00
networks.py Tecogan work 2020-10-07 09:03:30 -06:00
novograd.py Add novograd optimizer 2020-09-06 17:27:08 -06:00
SR_model.py Allow validating in batches, remove val size limit 2020-06-02 08:41:22 -06:00
SRGAN_model.py Fix up fea_loss calculator (for validation) 2020-10-03 11:19:20 -06:00