ZF/vit-pytorch
1
0
Fork 0
mirror of https://github.com/lucidrains/vit-pytorch.git synced 2025-12-30 08:02:29 +00:00
Code Issues Packages Projects Releases Wiki Activity
316 Commits 3 Branches 254 Tags
73199ab486e0fad9eced2e3350a11681db08b61b
Commit Graph

316 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
lucidrains
73199ab486 Nested navit (#325) 
add a variant of NaViT using nested tensors
1.7.7 		2024-08-20 15:12:29 -07:00
Phil Wang
4f22eae631 1.7.5 1.7.5 2024-08-07 08:46:18 -07:00
Phil Wang
dfc8df6713 add the u-vit implementation with simple vit + register tokens 2024-08-07 08:45:57 -07:00
lucidrains
9992a615d1 attention re-use in lookup vit should use pre-softmax attention matrix 1.7.4 2024-07-19 19:23:38 -07:00
Phil Wang
4b2c00cb63 when cross attending in look vit, make sure context tokens are normalized 1.7.3 2024-07-19 10:23:12 -07:00
Phil Wang
ec6c48b8ff norm not needed when reusing attention in lookvit 1.7.2 2024-07-19 10:00:03 -07:00
Phil Wang
547bf94d07 1.7.1 1.7.1 2024-07-19 09:49:44 -07:00
Phil Wang
bd72b58355 add lookup vit, cite, document later 2024-07-19 09:48:58 -07:00
lucidrains
e3256d77cd fix t2t vit having two layernorms, and make final layernorm in distillation wrapper configurable, default to False for vit 1.7.0 2024-06-11 15:12:53 -07:00
lucidrains
90be7233a3 rotary needs to be done with full precision to be safe 1.6.9 2024-05-11 08:04:32 -07:00
Phil Wang
bca88e9039 address https://github.com/lucidrains/vit-pytorch/issues/300 1.6.8 2024-05-02 08:46:39 -07:00
Phil Wang
96f66d2754 address https://github.com/lucidrains/vit-pytorch/issues/306 1.6.7 2024-04-18 09:44:29 -07:00
Phil Wang
12249dcc5f address https://github.com/lucidrains/vit-pytorch/issues/304 1.6.6 2024-04-17 09:40:03 -07:00
SOUMYADIP MAL
8b8da8dede Update setup.py (#303) 2024-04-17 08:21:30 -07:00
lucidrains
5578ac472f address https://github.com/lucidrains/vit-pytorch/issues/292 1.6.5 2023-12-23 08:11:39 -08:00
lucidrains
d446a41243 share an idea that should be tried if it has not been 1.6.4 2023-11-14 16:55:36 -08:00
lucidrains
0ad09c4cbc allow channels to be customizable for cvt 1.6.3a 2023-10-25 14:47:58 -07:00
Phil Wang
92b69321f4 1.6.2 1.6.2 2023-10-24 12:47:38 -07:00
Artem Lukin
fb4ac25174 Fix typo in LayerNorm (#285) 
Co-authored-by: Artem Lukin <artyom.lukin98@gmail.com>
 2023-10-24 12:47:21 -07:00
lucidrains
53fe345e85 no longer needed with einops 0.7 1.6.1 2023-10-19 18:16:46 -07:00
Phil Wang
efb94608ea readme 2023-10-19 09:38:35 -07:00
lucidrains
51310d1d07 add xcit diagram 2023-10-13 09:18:12 -07:00
Phil Wang
1616288e30 add xcit (#284) 
* add xcit

* use Rearrange layers

* give cross correlation transformer a final norm at end

* document
1.6.0 		2023-10-13 09:15:13 -07:00
Jason Chou
9e1e824385 Update README.md (#283) 
`patch_size` is size of patches, not number of patches
 2023-10-09 11:33:56 -07:00
lucidrains
bbb24e34d4 give a learned bias to and from registers for maxvit + register token variant 1.5.3 2023-10-06 10:40:26 -07:00
lucidrains
df8733d86e improvise a max vit with register tokens 2023-10-06 10:27:36 -07:00
lucidrains
680d446e46 document in readme later 2023-10-03 09:26:02 -07:00
lucidrains
3fdb8dd352 fix pypi 1.5.0a 2023-10-01 08:14:20 -07:00
lucidrains
a36546df23 add simple vit with register tokens example, cite 1.5.0 2023-10-01 08:11:40 -07:00
lucidrains
d830b05f06 address https://github.com/lucidrains/vit-pytorch/issues/279 1.4.5 2023-09-10 09:32:57 -07:00
Phil Wang
8208c859a5 just remove PreNorm wrapper from all ViTs, as it is unlikely to change at this point 1.4.4 2023-08-14 09:48:55 -07:00
Phil Wang
4264efd906 1.4.2 1.4.2 2023-08-14 07:59:35 -07:00
Phil Wang
b194359301 add a simple vit with qknorm, since authors seem to be promoting the technique on twitter 2023-08-14 07:58:45 -07:00
lucidrains
950c901b80 fix linear head in simple vit, thanks to @atkos 1.4.1 2023-08-10 14:36:21 -07:00
Phil Wang
3e5d1be6f0 address https://github.com/lucidrains/vit-pytorch/pull/274 1.4.0 2023-08-09 07:53:38 -07:00
Phil Wang
6e2393de95 wrap up NaViT 1.2.9 2023-07-25 10:38:55 -07:00
Phil Wang
32974c33df one can pass a callback to token_dropout_prob for NaViT that takes in height and width and calculate appropriate dropout rate 2023-07-24 14:52:40 -07:00
Phil Wang
17675e0de4 add constant token dropout for NaViT 1.2.7 2023-07-24 14:14:36 -07:00
Phil Wang
598cffab53 release NaViT 2023-07-24 13:55:54 -07:00
Phil Wang
23820bc54a begin work on NaViT (#273) 
finish core idea of NaViT
 2023-07-24 13:54:02 -07:00
Phil Wang
e9ca1f4d57 1.2.5 1.2.5 2023-07-24 06:43:24 -07:00
roydenwa
d4daf7bd0f Support SimpleViT as encoder in MAE (#272) 
support simplevit in mae
 2023-07-24 06:43:01 -07:00
Phil Wang
9e3fec2398 fix mpp 1.2.4 2023-06-28 08:02:43 -07:00
Phil Wang
ce4bcd08fb address https://github.com/lucidrains/vit-pytorch/issues/266 1.2.2 2023-05-20 08:24:49 -07:00
Phil Wang
ad4ca19775 enforce latest einops 1.2.1 2023-05-08 09:34:14 -07:00
Phil Wang
e1b08c15b9 fix tests 2023-03-19 10:52:47 -07:00
Phil Wang
c59843d7b8 add a version of simple vit using flash attention 1.2.0 2023-03-18 09:41:39 -07:00
lucidrains
9a8e509b27 separate a simple vit from mp3, so that simple vit can be used after being pretrained 2023-03-07 19:31:10 -08:00
Phil Wang
258dd8c7c6 release mp3, contributed by @Vishu26 1.1.0 2023-03-07 14:29:45 -08:00
Srikumar Sastry
4218556acd Add Masked Position Prediction (#260) 
* Create mp3.py

* Implementation: Position Prediction as an Effective Pretraining Strategy

* Added description for Masked Position Prediction

* MP3 image added
 2023-03-07 14:28:40 -08:00