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
layers
steps	Recurrent / teco work	2020-09-28 22:06:56 -06:00
__init__.py
base_model.py
ExtensibleTrainer.py
feature_model.py
loss.py
lr_scheduler.py
networks.py	spsr6	2020-09-28 22:09:27 -06:00
novograd.py
SR_model.py
SRGAN_model.py