DL-Art-School/codes/models
James Betker db52bec4ab spsr6
This is meant to be a variant of SPSR5 that harkens
back to the simpler earlier architectures that do not
have embeddings or ref_ inputs, but do have deep
multiplexers. It does, however, use some of the new
conjoin mechanisms.
2020-09-28 22:09:27 -06:00
..
archs spsr6 2020-09-28 22:09:27 -06:00
experiments Add in experiments hook 2020-09-19 10:05:25 -06:00
layers Add ImageFlowInjector 2020-09-19 10:07:00 -06:00
steps Recurrent / teco work 2020-09-28 22:06:56 -06:00
__init__.py ExtensibleTrainer work 2020-08-22 08:24:34 -06:00
base_model.py Don't load amp state dict if amp is disabled 2020-09-14 15:21:42 -06:00
ExtensibleTrainer.py Several things 2020-09-23 11:56:36 -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 spsr6 2020-09-28 22:09:27 -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 SRGAN_model/fullimgdataset compatibility 1 2020-09-08 11:34:35 -06:00