Phil Wang 4f3dbd003f for PiT, project to increased dimensions on first grouped conv for depthwise-conv

2021-04-29 12:41:00 -07:00

..

__init__.py

add deep vit

2021-03-23 11:57:13 -07:00

cait.py

add layer dropout for CaiT

2021-04-01 20:30:37 -07:00

cross_vit.py

add documentation for three recent vision transformer follow-up papers

2021-03-31 09:22:15 -07:00

cvt.py

fix norm issues in cvt

2021-04-27 08:36:17 -07:00

deepvit.py

add deep vit

2021-03-23 11:57:13 -07:00

distill.py

Fix alpha coefficient multiplication in the loss

2021-04-14 11:36:43 +02:00

efficient.py

make sure distillation still works

2021-02-21 19:08:18 -08:00

levit.py

add zeroing of weight parameters of batchnorm in levit just before residual connection, noticed by @EelcoHoogendoorn

2021-04-27 08:41:16 -07:00

local_vit.py

fix pooling bugs across a few new archs

2021-04-19 22:36:23 -07:00

mpp.py

cleanup and release 0.8.0

2021-03-08 07:28:31 -08:00

pit.py

for PiT, project to increased dimensions on first grouped conv for depthwise-conv

2021-04-29 12:41:00 -07:00

recorder.py

make recorder work for t2t and deepvit

2021-03-29 18:16:34 -07:00

rvt.py

cleanup rvt

2021-04-27 11:45:46 -07:00

t2t.py

remove masking, as it complicates with little benefit

2021-03-23 12:18:47 -07:00

vit.py

use hooks to retrieve attention maps for user without modifying ViT

2021-03-29 15:10:12 -07:00