Commit Graph

226 Commits

Author SHA1 Message Date
JacobLinCool
ab63fc9cc8 remove duplicated qkv computation in na_vit_nested_tensor_3d.py (#341) 2025-01-19 05:52:46 -08:00
Kale Kundert
b7ed6bad28 add option to set frame padding for 3D CCT (#339) 2025-01-04 07:55:27 -08:00
lucidrains
e7cba9ba6d add a simple vit flavor for a new bytedance paper that proposes to break out of the traditional one residual stream architecture - "hyper-connections" 2024-12-20 17:43:50 -08:00
lucidrains
56373c0cbd make value residual learned 2024-11-24 08:21:28 -08:00
lucidrains
24196a3e8a allow for qk norm to be turned off for na vit nested tensor 2024-11-20 10:59:22 -08:00
lucidrains
d47c57e32f fix tests 2024-11-10 09:43:54 -08:00
lucidrains
0449865786 update minimum version for nested tensor of NaViT 2024-11-10 09:37:48 -08:00
lucidrains
6693d47d0b update comment for navit 3d 2024-11-07 20:02:07 -08:00
Phil Wang
141239ca86 fix value residual 2024-10-31 06:48:24 -07:00
lucidrains
0b5c9b4559 add value residual based simple vit 2024-10-28 09:19:00 -07:00
lucidrains
e300cdd7dc fix multiheaded qk rmsnorm in nViT 2024-10-10 19:15:17 -07:00
Phil Wang
36ddc7a6ba go all the way with the normalized vit, fix some scales 2024-10-10 10:42:37 -07:00
Phil Wang
74b62009f8 go for multi-headed rmsnorm for the qknorm on hypersphere vit 2024-10-10 08:09:58 -07:00
Phil Wang
f50d7d1436 add a hypersphere vit, adapted from https://arxiv.org/abs/2410.01131 2024-10-09 07:32:25 -07:00
lucidrains
82f2fa751d address https://github.com/lucidrains/vit-pytorch/issues/330 2024-10-04 07:01:48 -07:00
lucidrains
fcb9501cdd add register tokens to the nested tensor 3d na vit example for researcher 2024-08-28 12:21:31 -07:00
roydenwa
9d43e4d0bb Add ViViT variant with factorized self-attention (#327)
* Add FactorizedTransformer

* Add variant param and check in fwd method

* Check if variant is implemented

* Describe new ViViT variant
2024-08-21 19:23:38 -07:00
Phil Wang
5e808f48d1 3d version of navit nested tensor 2024-08-21 07:23:21 -07:00
lucidrains
73199ab486 Nested navit (#325)
add a variant of NaViT using nested tensors
2024-08-20 15:12:29 -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 2024-07-19 19:23:38 -07:00
Phil Wang
4b2c00cb63 when cross attending in look vit, make sure context tokens are normalized 2024-07-19 10:23:12 -07:00
Phil Wang
ec6c48b8ff norm not needed when reusing attention in lookvit 2024-07-19 10:00:03 -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 2024-06-11 15:12:53 -07:00
lucidrains
90be7233a3 rotary needs to be done with full precision to be safe 2024-05-11 08:04:32 -07:00
Phil Wang
bca88e9039 address https://github.com/lucidrains/vit-pytorch/issues/300 2024-05-02 08:46:39 -07:00
Phil Wang
96f66d2754 address https://github.com/lucidrains/vit-pytorch/issues/306 2024-04-18 09:44:29 -07:00
Phil Wang
12249dcc5f address https://github.com/lucidrains/vit-pytorch/issues/304 2024-04-17 09:40:03 -07:00
lucidrains
5578ac472f address https://github.com/lucidrains/vit-pytorch/issues/292 2023-12-23 08:11:39 -08:00
lucidrains
d446a41243 share an idea that should be tried if it has not been 2023-11-14 16:55:36 -08:00
lucidrains
0ad09c4cbc allow channels to be customizable for cvt 2023-10-25 14:47:58 -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 2023-10-19 18:16:46 -07:00
Phil Wang
1616288e30 add xcit (#284)
* add xcit

* use Rearrange layers

* give cross correlation transformer a final norm at end

* document
2023-10-13 09:15:13 -07:00
lucidrains
bbb24e34d4 give a learned bias to and from registers for maxvit + register token variant 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
a36546df23 add simple vit with register tokens example, cite 2023-10-01 08:11:40 -07:00
lucidrains
d830b05f06 address https://github.com/lucidrains/vit-pytorch/issues/279 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 2023-08-14 09:48:55 -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 2023-08-10 14:36:21 -07:00
Phil Wang
3e5d1be6f0 address https://github.com/lucidrains/vit-pytorch/pull/274 2023-08-09 07:53:38 -07:00
Phil Wang
6e2393de95 wrap up NaViT 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 2023-07-24 14:14:36 -07:00
Phil Wang
23820bc54a begin work on NaViT (#273)
finish core idea of NaViT
2023-07-24 13:54:02 -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 2023-06-28 08:02:43 -07:00