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
..
.idea
data	Don't apply jpeg corruption & noise corruption together	2020-10-20 12:56:35 -06:00
metrics
models	Collapse progressive zoom candidates into the batch dimension	2020-10-21 22:37:23 -06:00
scripts	Misc	2020-10-21 11:08:21 -06:00
switched_conv@cb520afd4d	Update SwitchedConv	2020-10-13 20:57:12 -06:00
utils	Codebase cleanup	2020-10-13 20:56:39 -06:00
process_video.py	Fix process_video	2020-10-21 11:08:12 -06:00
requirements.txt	Add missing requirements	2020-09-09 10:46:08 -06:00
test.py	Restore test.py for use as standalone validator	2020-10-19 15:26:07 -06:00
train2.py	ChainedGen: Output debugging information on blocks	2020-10-21 16:36:23 -06:00
train.py	ChainedGen: Output debugging information on blocks	2020-10-21 16:36:23 -06:00