Ross Wightman
4634c3e134
Version 1.0.4.dev0
2024-05-20 15:52:27 -07:00
Fernando Cossio
9b11801cb4
Credit earlier work with the same idea.
...
Hi, this earlier work has the same name and idea behind this layer. It could be useful for readers to keep both links here if they want to see the effects of introducing this layer on a very different domain. 😄
2024-05-16 22:50:34 +02:00
Ross Wightman
cb0e4391be
Release 1.0.3
2024-05-15 11:06:22 -07:00
Ross Wightman
27fd2f35d3
Merge pull request #2181 from huggingface/Delaunay-dist-backend
...
Delaunay dist backend flag
2024-05-15 10:00:59 -07:00
Ross Wightman
e57625e814
Tweak dist_backend to use device_type (before possible :)
2024-05-15 08:49:25 -07:00
Ross Wightman
6ca92570f7
Merge branch 'patch-1' of https://github.com/Delaunay/pytorch-image-models into Delaunay-dist-backend
2024-05-15 08:40:58 -07:00
Ross Wightman
cd0e7b11ff
Merge pull request #2180 from yvonwin/main
...
Remove a duplicate function in mobilenetv3.py
2024-05-15 07:54:17 -07:00
Ross Wightman
83aee5c28c
Add explicit GAP (avg pool) variants of other SigLIP models.
2024-05-15 07:53:19 -07:00
yvonwin
58f2f79b04
Remove a duplicate function in mobilenetv3.py: _gen_lcnet is repeated in mobilenetv3.py.Remove the duplicate code.
2024-05-15 17:59:34 +08:00
Ross Wightman
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
Ross Wightman
cc5f2f6f70
version 1.0.2dev0
2024-05-13 15:25:15 -07:00
Ross Wightman
3bfd036b58
Add normalize flag to transforms factory, allow return of non-normalized native dtype torch.Tensors
2024-05-13 15:23:25 -07:00
Ross Wightman
a69863ad61
Merge pull request #2156 from huggingface/hiera
...
WIP Hiera implementation.
2024-05-13 14:58:12 -07:00
Setepenre
8848dad362
Update distributed.py
2024-05-13 16:55:42 -04:00
Ross Wightman
f7aa0a1a71
Add missing vit_wee weight
2024-05-13 12:05:47 -07:00
Ross Wightman
7a4e987b9f
Hiera weights on hub
2024-05-13 11:43:22 -07:00
Ross Wightman
c838c4233f
Add typing to reset_classifier() on other models
2024-05-12 11:12:00 -07:00
Ross Wightman
3e03b2bf3f
Fix a few more hiera API issues
2024-05-12 11:11:45 -07:00
Ross Wightman
211d18d8ac
Move norm & pool into Hiera ClassifierHead. Misc fixes, update features_intermediate() naming
2024-05-11 23:37:35 -07:00
Ross Wightman
2ca45a4ff5
Merge remote-tracking branch 'upstream/main' into hiera
2024-05-11 15:43:05 -07:00
Ross Wightman
1d3ab176bc
Remove debug / staging code
2024-05-10 22:16:34 -07:00
Ross Wightman
aa4d06a11c
sbb vit weights on hub, testing
2024-05-10 17:15:01 -07:00
Ross Wightman
3582ca499e
Prepping weight push, benchmarking.
2024-05-10 14:14:06 -07:00
Ross Wightman
2bfa5e5d74
Remove JIT activations, take jit out of ME activations. Remove other instances of torch.jit.script. Breaks torch.compile and is much less performant. Remove SpaceToDepthModule
2024-05-06 16:32:49 -07:00
Ross Wightman
07535f408a
Add AttentionExtract helper module
2024-05-04 14:10:00 -07:00
Ross Wightman
45b7ae8029
forward_intermediates() support for byob/byoanet models
2024-05-04 14:06:52 -07:00
Ross Wightman
c4b8897e9e
attention -> attn in davit for model consistency
2024-05-04 14:06:11 -07:00
Ross Wightman
cb57a96862
Fix early stop for efficientnet/mobilenetv3 fwd inter. Fix indices typing for all fwd inter.
2024-05-04 10:21:58 -07:00
Ross Wightman
01dd01b70e
forward_intermediates() for MlpMixer models and RegNet.
2024-05-04 10:21:03 -07:00
Ross Wightman
f8979d4f50
Comment out time local files while testing new vit weights
2024-05-03 20:26:56 -07:00
Ross Wightman
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
Ross Wightman
301d0bb21f
Stricter check on pool_type for adaptive pooling module. Fix #2159
2024-05-03 16:16:51 -07:00
Ross Wightman
d6da4fb01e
Add forward_intermediates() to efficientnet / mobilenetv3 based models as an exercise.
2024-05-02 14:19:16 -07:00
Ross Wightman
c22efb9765
Add wee & little vits for some experiments
2024-05-02 10:51:35 -07:00
Ross Wightman
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
user-miner1
740f4983b3
Assert messages added
2024-04-30 10:10:02 +03:00
Ross Wightman
c6db4043cd
Update forward_intermediates for hiera to have its own fwd impl w/ early stopping. Remove return_intermediates bool from forward(). Still an fx issue with None mask arg :(
2024-04-29 17:23:37 -07:00
Ross Wightman
9b9a356a04
Add forward_intermediates support for xcit, cait, and volo.
2024-04-29 16:30:45 -07:00
Ross Wightman
ef147fd2fb
Add forward_intermediates API to Hiera for features_only=True support
2024-04-21 11:30:41 -07:00
Ross Wightman
d88bed6535
Bit more Hiera fiddling
2024-04-21 09:36:57 -07:00
Ross Wightman
8a54d2a930
WIP Hiera implementation. Fix #2083 . Trying to get image size adaptation to work.
2024-04-20 09:47:17 -07:00
Ross Wightman
de15b8b828
Next release will be 1.0 :o
2024-04-11 08:55:27 -07:00
Ross Wightman
c8da47a773
Update version.py
2024-04-11 08:45:50 -07:00
Ross Wightman
d6b95520f1
Merge pull request #2136 from huggingface/vit_features_only
...
Exploring vit features_only via new forward_intermediates() API, inspired by #2131
2024-04-11 08:38:20 -07:00
Ross Wightman
24f6d4f7f8
Fix #2127 move to ema device
2024-04-10 21:29:09 -07:00
Ross Wightman
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
Ross Wightman
ef9c6fb846
forward_head(), consistent pre_logits handling to reduce likelihood of people manually replacing .head module having issues
2024-04-09 21:54:59 -07:00
Ross Wightman
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
Ross Wightman
c28ee2e904
Merge pull request #2145 from huggingface/fix_imagenet22k_ms_mapping
...
Add teddy-bear class back to first 1000 classes of imagenet22k_ms_synsets (line 851, index 850)
2024-04-09 14:56:31 -07:00
Ross Wightman
f5ea076a46
Merge pull request #2143 from huggingface/fix_asymm_set_grad_enable
...
Fix #2132 , remove use of _C.set_grad_enable. Line endings were messed up too
2024-04-09 10:14:13 -07:00
