1031 Commits

Author SHA1 Message Date
pUmpKin-Co
8556462a18 fix doc typo in resnetv2 2023-10-20 11:56:50 -07:00
Ross Wightman
462fb3ec9f Push new repvit weights to hub, tweak tag names 2023-10-20 11:49:29 -07:00
Ross Wightman
5309424d5e Merge branch 'main' of https://github.com/jameslahm/pytorch-image-models into jameslahm-main 2023-10-20 11:08:12 -07:00
Ross Wightman
d3ebdcfd93 Disable strict load when siglip vit pooling removed 2023-10-19 12:03:40 -07:00
Ross Wightman
e728f3efdb Cleanup ijepa models, they're just gap (global-avg-pool) models w/o heads. fc-norm conversion was wrong, gigantic should have been giant 2023-10-17 15:44:46 -07:00
Ross Wightman
49a459e8f1 Merge remote-tracking branch 'upstream/main' into vit_siglip_and_reg 2023-10-17 09:36:48 -07:00
Ross Wightman
59b622233b Change ijepa names, add pretrain cfg for reg experimentts 2023-10-17 07:16:17 -07:00
Ross Wightman
71365165a2 Add SigLIP weights 2023-10-16 23:26:08 -07:00
Ross Wightman
42daa3b497 Add full set of SigLIP models 2023-10-10 22:15:45 -07:00
Yassine
884ef88818 fix all SDPA dropouts 2023-10-05 08:58:41 -07:00
Yassine
b500cae4c5 fastvit: don't dropout in eval 2023-10-05 08:58:41 -07:00
Ross Wightman
b9dde58076 Fixup attention pooling in siglip vit support 2023-10-02 11:44:12 -07:00
jameslahm
f061b539d7 Update RepViT models 2023-10-01 14:00:53 +08:00
Ross Wightman
99cfd6702f Use global pool arg to select attention pooling in head 2023-09-30 16:16:21 -07:00
Ross Wightman
82cc53237e Working on support for siglip (w/ attn pool) vit backbone, and adding registers (reg tokens) 2023-09-30 16:03:01 -07:00
Ross Wightman
6bae514656 Add pretrained patch embed resizing to swin 2023-09-27 10:27:28 -07:00
Yassine
5c504b4ded flip these two 2023-09-27 10:24:12 -07:00
Yassine
8ba2038e6b fast_vit: propagate act_layer argument 2023-09-27 10:24:12 -07:00
Nguyen Nhat Hoang
95ba90157f Update tiny_vit.py to fix bug 2023-09-23 10:05:52 -07:00
belfner
245ad4f41a Added missing RuntimeError to builder functions of models that do not currently support feature extraction 2023-09-19 08:19:14 -07:00
Thorsten Hempel
d4c21b95f4 Update repghost.py 2023-09-15 11:41:56 -07:00
Thorsten Hempel
7eb7d13845 Fix in_features for linear layer in reset_classifier. 2023-09-13 09:29:38 -07:00
Ross Wightman
0d124ffd4f Update README. Fine-grained layer-wise lr decay working for tiny_vit and both efficientvits. Minor fixes. 2023-09-01 15:05:29 -07:00
Ross Wightman
2f0fbb59b3 TinyViT weights on HF hub 2023-09-01 11:05:56 -07:00
Ross Wightman
507cb08acf TinyVitBlock needs adding as leaf for FX now, tweak a few dim names 2023-09-01 11:05:56 -07:00
Ross Wightman
9caf32b93f Move levit style pos bias resize with other rel pos bias utils 2023-09-01 11:05:56 -07:00
Ross Wightman
63417b438f TinyViT adjustments
* keep most of net in BCHW layout, performance appears same, can remove static resolution attribs and features easier to use
* add F.sdpa, decent gains in pt 2.1
* tweak crop pct based on eval
2023-09-01 11:05:56 -07:00
方曦
39aa44b192 Fixing tinyvit trace issue 2023-09-01 11:05:56 -07:00
方曦
aea3b9c854 Fixing tinyvit input_size issue 2023-09-01 11:05:56 -07:00
方曦
fabc4e5bcd Fixing tinyvit torchscript issue 2023-09-01 11:05:56 -07:00
方曦
bae949f830 fix attention_bias_cache in tinyvit 2023-09-01 11:05:56 -07:00
方曦
170a5b6e27 add tinyvit 2023-09-01 11:05:56 -07:00
Ross Wightman
983310d6a2 Fix #1935 , torch.amp.autocast -> torch.autocast (namespace issue for 1.10 pt compat) 2023-08-30 15:03:28 -07:00
Ross Wightman
c8b2f28096 Fix a few typos, fix fastvit proj_drop, add code link 2023-08-28 21:26:29 -07:00
Ross Wightman
fc5d705b83 dynamic_size -> dynamic_img_size, add dynamic_img_pad for padding option 2023-08-27 15:58:35 -07:00
Ross Wightman
1f4512fca3 Support dynamic_resize in eva.py models 2023-08-27 15:58:35 -07:00
Ross Wightman
ea3519a5f0 Fix dynamic_resize for deit models (distilled or no_embed_cls) and vit w/o class tokens 2023-08-27 15:58:35 -07:00
Ross Wightman
4d8ecde6cc Fix torchscript for vit-hybrid dynamic_resize 2023-08-27 15:58:35 -07:00
Ross Wightman
fdd8c7c2da Initial impl of dynamic resize for existing vit models (incl vit-resnet hybrids) 2023-08-27 15:58:35 -07:00
Ross Wightman
5d599a6a10 RepViT weights on HF hub 2023-08-25 10:39:02 -07:00
Ross Wightman
56c285445c Wrong pool size for 384x384 inception_next_base 2023-08-24 18:31:44 -07:00
Ross Wightman
af9f56f3bf inception_next dilation support, weights on hf hub, classifier reset / global pool / no head fixes 2023-08-24 18:31:44 -07:00
Ross Wightman
2d33b9df6c Add features_only support to inception_next 2023-08-24 18:31:44 -07:00
Ross Wightman
3d8d7450ad InceptionNeXt using timm builder, more cleanup 2023-08-24 18:31:44 -07:00
Ross Wightman
f4cf9775c3 Adding InceptionNeXt 2023-08-24 18:31:44 -07:00
Ross Wightman
d6c348765a Fix first_conv for mobileone and fastvit 2023-08-23 22:50:37 -07:00
Ross Wightman
16334e4bec Fix two fastvit issues 2023-08-23 22:50:37 -07:00
Ross Wightman
5242ba6edc MobileOne and FastViT weights on HF hub, more code cleanup and tweaks, features_only working. Add reparam flag to validate and benchmark, support reparm of all models with fuse(), reparameterize() or switch_to_deploy() methods on modules 2023-08-23 22:50:37 -07:00
Ross Wightman
40dbaafef5 Stagify FastViT /w downsample to top of stage 2023-08-23 22:50:37 -07:00
Ross Wightman
8470eb1cb5 More fastvit & mobileone updates, ready for weight upload 2023-08-23 22:50:37 -07:00