a5a2ad2e48
Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size
...
* add test that model supports forward_head(x, pre_logits=True)
* add head_hidden_size attr to all models and set differently from num_features attr when head has hidden layers
* test forward_features() feat dim == model.num_features and pre_logits feat dim == self.head_hidden_size
* more consistency in reset_classifier signature, add typing
* asserts in some heads where pooling cannot be disabled
Fix #2194
2024-06-07 13:53:00 -07:00
cc8a03daac
Add ConvStem and MobileCLIP hybrid model for B variant. Add full norm disable support to ConvNormAct layers
2024-06-06 09:15:27 -07:00
1b66ec7cf3
Fixup ViTamin, add hub weight reference
2024-06-03 17:14:03 -07:00
5dce710101
Add vit_little in12k + in12k-ft-in1k weights
2024-05-27 14:56:03 -07:00
84cb225ecb
Add in12k + 12k_ft_in1k vit_medium weights
2024-05-20 15:52:46 -07:00
83aee5c28c
Add explicit GAP (avg pool) variants of other SigLIP models.
2024-05-15 07:53:19 -07:00
7b3b11b63f
Support loading of paligemma weights into GAP variants of SigLIP ViT. Minor tweak to npz loading for packed transformer weights.
2024-05-14 15:44:37 -07:00
a69863ad61
Merge pull request #2156 from huggingface/hiera
...
WIP Hiera implementation.
2024-05-13 14:58:12 -07:00
f7aa0a1a71
Add missing vit_wee weight
2024-05-13 12:05:47 -07:00
c838c4233f
Add typing to reset_classifier() on other models
2024-05-12 11:12:00 -07:00
1d3ab176bc
Remove debug / staging code
2024-05-10 22:16:34 -07:00
aa4d06a11c
sbb vit weights on hub, testing
2024-05-10 17:15:01 -07:00
3582ca499e
Prepping weight push, benchmarking.
2024-05-10 14:14:06 -07:00
cb57a96862
Fix early stop for efficientnet/mobilenetv3 fwd inter. Fix indices typing for all fwd inter.
2024-05-04 10:21:58 -07:00
f8979d4f50
Comment out time local files while testing new vit weights
2024-05-03 20:26:56 -07:00
c719f7eb86
More forward_intermediates() updates
...
* add convnext, resnet, efficientformer, levit support
* remove kwargs only for fn so that torchscript isn't broken for all :(
* use reset_classifier() consistently in prune
2024-05-03 16:22:32 -07:00
c22efb9765
Add wee & little vits for some experiments
2024-05-02 10:51:35 -07:00
67332fce24
Add features_intermediate() support to coatnet, maxvit, swin* models. Refine feature interface. Start prep of new vit weights.
2024-04-30 16:56:33 -07:00
4b2565e4cb
More forward_intermediates() / FeatureGetterNet work
...
* include relpos vit
* refactor reduction / size calcs so hybrid vits work and dynamic_img_size works
* fix -ve feature indices when pruning
* fix mvitv2 w/ class token
* refine naming
* add tests
2024-04-10 15:11:34 -07:00
679daef76a
More forward_intermediates() & features_only work
...
* forward_intermediates() added to beit, deit, eva, mvitv2, twins, vit, vit_sam
* add features_only to forward intermediates to allow just intermediate features
* fix #2060
* fix #1374
* fix #657
2024-04-09 21:29:16 -07:00
5fdc0b4e93
Exploring vit features_only using get_intermediate_layers() as per #2131
2024-04-07 11:24:45 -07:00
c559c3911f
Improve vit conversions. OpenAI convert pass through main convert for patch & pos resize. Fix #2120
2024-03-21 10:00:43 -07:00
256cf19148
Rename tinyclip models to fit existing 'clip' variants, use consistently mapped OpenCLIP compatible checkpoint on hf hub
2024-03-20 15:21:46 -07:00
1a1d07d479
add other tinyclip
2024-03-19 07:27:09 +08:00
dfffffac55
add tinyclip 8m
2024-03-19 07:02:17 +08:00
db06b56d34
Saved computational costs of get_intermediate_layers() from unused blocks
2024-03-17 21:34:06 +08:00
4731e4efc4
Modified ViT get_intermediate_layers() to support dynamic image size
2024-03-16 23:07:21 +08:00
ac1b08deb6
fix_init on vit & relpos vit
2024-02-10 20:15:37 -08:00
87fec3dc14
Update experimental vit model configs
2024-02-10 16:05:58 -08:00
ada145b016
Literal use w/ python < 3.8 requires typing_extension, cach instead of check sys ver
2023-11-21 09:48:03 -08:00
21647c0a0c
Add types to vision_transformers.py
2023-11-17 16:06:06 -08:00
7c685a4ef3
Fix openai quickgelu loading and add mnissing orig_in21k vit weights and remove zero'd classifier w/ matching hub update
2023-11-16 19:16:28 -08:00
dcfdba1f5f
Make quickgelu models appear in listing
2023-11-03 11:01:41 -07:00
96bd162ddb
Add cc-by-nc-4.0 license for metaclip, make note in quickgelu model def about pretrained_cfg mapping
2023-11-03 11:01:41 -07:00
6894ec7edc
Forgot about datcomp b32 models
2023-11-03 11:01:41 -07:00
a2e4a4c148
Add quickgelu vit clip variants, simplify get_norm_layer and allow string args in vit norm/act. Add metaclip CLIP weights
2023-11-03 11:01:41 -07:00
c55bc41a42
DFN CLIP ViT support
2023-10-31 12:16:21 -07:00
68a121402f
Added hub weights for dinov2 register models
2023-10-29 23:03:48 -07:00
3f02392488
Add DINOv2 models with register tokens. Convert pos embed to non-overlapping for consistency.
2023-10-29 23:03:48 -07:00
97450d618a
Update DINOv2 license to Apache 2.0
2023-10-27 09:12:51 -07:00
d3ebdcfd93
Disable strict load when siglip vit pooling removed
2023-10-19 12:03:40 -07:00
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
49a459e8f1
Merge remote-tracking branch 'upstream/main' into vit_siglip_and_reg
2023-10-17 09:36:48 -07:00
59b622233b
Change ijepa names, add pretrain cfg for reg experimentts
2023-10-17 07:16:17 -07:00
71365165a2
Add SigLIP weights
2023-10-16 23:26:08 -07:00
42daa3b497
Add full set of SigLIP models
2023-10-10 22:15:45 -07:00
884ef88818
fix all SDPA dropouts
2023-10-05 08:58:41 -07:00
b9dde58076
Fixup attention pooling in siglip vit support
2023-10-02 11:44:12 -07:00
99cfd6702f
Use global pool arg to select attention pooling in head
2023-09-30 16:16:21 -07:00
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
Ross Wightman
Thien Tran
Cheng-Ling Lai
Laureηt
Patrick Labatut
Yassine