James Betker 42a10b34ce Re-enable batch norm on switch processing blocks ... Found out that batch norm is causing the switches to init really poorly - not using a significant number of transforms. Might be a great time to re-consider using the attention norm, but for now just re-enable it.		2020-06-24 21:15:17 -06:00
..
.idea	IDEA update	2020-05-19 09:35:26 -06:00
data	Add doResizeLoss to dataset	2020-06-08 11:27:06 -06:00
data_scripts	Add simple resize to extract images	2020-06-23 09:39:51 -06:00
metrics	mmsr	2019-08-23 21:42:47 +08:00
models	Re-enable batch norm on switch processing blocks	2020-06-24 21:15:17 -06:00
options	Add dynamic video processing script	2020-05-27 17:09:11 -06:00
scripts	mmsr	2019-08-23 21:42:47 +08:00
temp	Misc changes	2020-05-14 20:45:38 -06:00
utils	Add GPU mem tracing module	2020-06-14 11:02:54 -06:00
distill_torchscript.py	Misc	2020-06-14 11:03:02 -06:00
onnx_inference.py	Misc	2020-06-14 11:03:02 -06:00
process_video.py	Debug process_video	2020-05-29 20:44:50 -06:00
requirements.txt	Introduce (untested) colab mode	2020-06-01 15:09:52 -06:00
run_scripts.sh	mmsr	2019-08-23 21:42:47 +08:00
test.py	Misc	2020-06-02 09:35:52 -06:00
train.py	Log tensorboard directly into experiments directory	2020-06-18 11:33:02 -06:00