lucidrains
|
0ad09c4cbc
|
allow channels to be customizable for cvt
|
2023-10-25 14:47:58 -07:00 |
|
Phil Wang
|
8208c859a5
|
just remove PreNorm wrapper from all ViTs, as it is unlikely to change at this point
|
2023-08-14 09:48:55 -07:00 |
|
Phil Wang
|
4ef72fc4dc
|
add EsViT, by popular request, an alternative to Dino that is compatible with efficient ViTs with accounting for regional self-supervised loss
|
2022-05-03 10:29:29 -07:00 |
|
Phil Wang
|
4e6a42a0ca
|
correct need for post-attention dropout
|
2022-03-30 10:50:57 -07:00 |
|
Phil Wang
|
64a07f50e6
|
epsilon should be inside square root
|
2022-01-24 17:24:41 -08:00 |
|
Phil Wang
|
3df6c31c61
|
fix norm issues in cvt
|
2021-04-27 08:36:17 -07:00 |
|
Phil Wang
|
54af220930
|
fix cvt
|
2021-04-26 20:37:51 -07:00 |
|
Phil Wang
|
506fcf83a6
|
add documentation for three recent vision transformer follow-up papers
|
2021-03-31 09:22:15 -07:00 |
|
Phil Wang
|
6fb360a1ff
|
add arxiv links for now, document in readme later
|
2021-03-30 22:26:44 -07:00 |
|
Phil Wang
|
4b9a02d89c
|
use depthwise conv for CvT projections
|
2021-03-30 18:18:35 -07:00 |
|
Phil Wang
|
518924eac5
|
add CvT
|
2021-03-30 14:42:39 -07:00 |
|