James Betker 43c4f92123 Collapse progressive zoom candidates into the batch dimension ... This contributes a significant speedup to training this type of network since losses can operate on the entire prediction spectrum at once.		2020-10-21 22:37:23 -06:00
..
archs	Add a ChainedEmbeddingGen which can be simueltaneously used with multiple training paradigms	2020-10-21 22:21:51 -06:00
experiments
flownet2@2e9e010c98	Integrate flownet2 into codebase, add teco visual debugs	2020-10-06 20:35:39 -06:00
steps	Collapse progressive zoom candidates into the batch dimension	2020-10-21 22:37:23 -06:00
base_model.py	Go back to torch's DDP	2020-10-16 20:47:35 -06:00
ExtensibleTrainer.py	Enable ExtensibleTrainer to skip steps when state keys are missing	2020-10-21 22:22:28 -06:00
feature_model.py
loss.py	Add spread loss	2020-10-19 11:31:19 -06:00
lr_scheduler.py
networks.py	Add a ChainedEmbeddingGen which can be simueltaneously used with multiple training paradigms	2020-10-21 22:21:51 -06:00