James Betker c8ab89d243 Add model swapout ... Model swapout is a feature where, at specified intervals, a random D and G model will be swapped in place for the one being trained. After a short period of time, this model is swapped back out. This is intended to increase training diversity.		2020-05-13 16:53:38 -06:00
..
data	Cap test workers at 10	2020-05-13 09:20:45 -06:00
data_scripts	Some random fixes/adjustments	2020-04-22 00:38:53 -06:00
metrics	mmsr	2019-08-23 21:42:47 +08:00
models	Add model swapout	2020-05-13 16:53:38 -06:00
options	Add model swapout	2020-05-13 16:53:38 -06:00
scripts	mmsr	2019-08-23 21:42:47 +08:00
temp	Fix megabatch scaling, log low and med-res gen images	2020-05-05 08:34:57 -06:00
utils	mmsr	2019-08-23 21:42:47 +08:00
distill_torchscript.py	Add code for compiling model to torchscript	2020-05-13 09:21:13 -06:00
requirements.txt	Create requirements.txt	2019-11-24 07:48:52 +00:00
run_scripts.sh	mmsr	2019-08-23 21:42:47 +08:00
test_Vid4_REDS4_with_GT_DUF.py	mmsr	2019-08-23 21:42:47 +08:00
test_Vid4_REDS4_with_GT_TOF.py	mmsr	2019-08-23 21:42:47 +08:00
test_Vid4_REDS4_with_GT.py	mmsr	2019-08-23 21:42:47 +08:00
test.py	Config updates	2020-05-13 09:20:28 -06:00
train.py	Config updates	2020-05-13 09:20:28 -06:00