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
07535f408a
Add AttentionExtract helper module
2024-05-04 14:10:00 -07:00
45b7ae8029
forward_intermediates() support for byob/byoanet models
2024-05-04 14:06:52 -07:00
c4b8897e9e
attention -> attn in davit for model consistency
2024-05-04 14:06:11 -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
01dd01b70e
forward_intermediates() for MlpMixer models and RegNet.
2024-05-04 10:21:03 -07:00
f8979d4f50
Comment out time local files while testing new vit weights
2024-05-03 20:26:56 -07:00
3e7ab12af9
Merge pull request #2165 from huggingface/more_vits_better_getter
...
Add features_intermediate() support to coatnet, maxvit, swin*. Tweak feature extraction interfaces. Prep new vit weights while testing.
2024-05-03 19:26:01 -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
301d0bb21f
Stricter check on pool_type for adaptive pooling module. Fix #2159
2024-05-03 16:16:51 -07:00
d6da4fb01e
Add forward_intermediates() to efficientnet / mobilenetv3 based models as an exercise.
2024-05-02 14:19:16 -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
62516d525a
Merge pull request #2164 from ZFTurbo/main
...
Assert messages added
2024-04-30 10:13:38 -07:00
740f4983b3
Assert messages added
2024-04-30 10:10:02 +03:00
6de529bb3c
Merge pull request #2162 from huggingface/more_fwd_intermediates
...
Add forward_intermediates support for xcit, cait, and volo.
2024-04-29 21:09:57 -07:00
63970e4e61
Update tests for volo/cait/xcit forward_intermediates
2024-04-29 17:19:11 -07:00
9b9a356a04
Add forward_intermediates support for xcit, cait, and volo.
2024-04-29 16:30:45 -07:00
e741370e2b
Update README.md
2024-04-11 10:16:39 -07:00
de15b8b828
Next release will be 1.0 :o
2024-04-11 08:55:27 -07:00
c8da47a773
Update version.py
2024-04-11 08:45:50 -07:00
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
24f6d4f7f8
Fix #2127 move to ema device
2024-04-10 21:29:09 -07:00
fe3cf542fa
Fix / improve tests for features
2024-04-10 21:14:02 -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
e25bbfceec
Fix #2097 a small typo in train.py
2024-04-10 09:40:14 -07:00
195d12fdff
Add missing device argument to inference.py dataloader
2024-04-10 09:34:34 -07:00
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
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
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
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
9531eb793c
Merge pull request #2142 from huggingface/fix_hrnet_head
...
Fix #2139 , disable strict weight loading when head changes from classification
2024-04-09 10:04:09 -07:00
286d941923
Add teddy-bear class back to first 1000 classes of imagenet22k_ms_synsets (index 851)
2024-04-09 09:33:08 -07:00
5c5ae8d401
Fix #2132 , remove use of _C.set_grad_enable. Line endings were messed up too
2024-04-09 09:00:23 -07:00
17b892f703
Fix #2139 , disable strict weight loading when head changes from classification
2024-04-09 08:41:37 -07:00
5fdc0b4e93
Exploring vit features_only using get_intermediate_layers() as per #2131
2024-04-07 11:24:45 -07:00
59b3d86c1d
Merge pull request #2124 from fzyzcjy/patch-1
...
Fix super tiny type error
2024-04-02 14:31:38 -07:00
b44e4e45a2
more
2024-04-02 10:25:30 +08:00
8880a5cd5c
Update scheduler.py
2024-03-23 11:27:33 +08:00
67b0b3d7c7
Merge pull request #2121 from huggingface/cleanup_vit_convert
...
Improve vit conversions. OpenAI convert pass through main convert
2024-03-21 13:13:53 -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
492947d129
Merge pull request #2113 from gau-nernst/tinyclip
...
Add TinyCLIP
2024-03-20 16:22:08 -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
111fad1a9f
Add first CPU inference benchmark, using torch.compile
2024-03-20 08:43:29 -07:00
4c743769ff
Merge pull request #2117 from mwalmsley/patch-1
...
Update hf_hub.mdx with new import, rename labels
2024-03-19 12:54:07 -07:00
496ba54485
Update hf_hub.mdx with new import, rename labels
...
Change suggested import from timm.models.hub.push_to_hf_hub to timm.models.push_to_hf_hub
timm.models.hub.push_to_hf_hub import fails because of refactor. timm now uses _hub.py
https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/_hub.py#L270
which is imported into timm.models.__init__
6ccb7d6a7c/timm/models/__init__.py (L87)
2024-03-19 13:39:21 -04:00
1a1d07d479
add other tinyclip
2024-03-19 07:27:09 +08:00
dfffffac55
add tinyclip 8m
2024-03-19 07:02:17 +08:00
6ccb7d6a7c
Merge pull request #2111 from jamesljlster/enhance_vit_get_intermediate_layers
...
Vision Transformer (ViT) get_intermediate_layers: enhanced to support dynamic image size and saved computational costs from unused blocks
2024-03-18 13:41:18 -07:00
db06b56d34
Saved computational costs of get_intermediate_layers() from unused blocks
2024-03-17 21:34:06 +08:00
Ross Wightman
Ross Wightman
user-miner1
fzyzcjy
fzyzcjy
Mike Walmsley
Thien Tran
Cheng-Ling Lai