320bf9c469
Remove redundant types, kwargs back in own section (lesser of many evils?)
2023-05-01 14:21:48 -07:00
8fa86a28a8
Add datacomp L/14 (79.2 zs) image tower weights
2023-05-01 10:24:08 -07:00
5e64777804
0.8.21dev0
2023-04-28 13:46:59 -07:00
493c730ffc
Fix pit regression
2023-04-26 23:16:06 -07:00
437d344e03
Always some torchscript issues
2023-04-26 20:42:34 -07:00
528faa0e04
Some fixes
2023-04-26 17:46:20 -07:00
3386af8c86
Final push to get remaining models using multi-weight pretrained configs, almost all weights on HF hub
2023-04-26 15:52:13 -07:00
c0560cbf22
version 0.8.20dev0
2023-04-21 16:57:32 -07:00
7ad7ddb7ad
DenseNet, DPN, VoVNet, Aligned Xception weights on HF hub. DenseNet grad_checkpointing using timm API
2023-04-21 16:56:44 -07:00
864bfd43d0
hardcore nas weights on hf hub
2023-04-21 14:35:10 -07:00
6e4529ae35
TResNet weights now on HF hub, modified to remove InplaceABN dependency
2023-04-21 14:20:48 -07:00
04dcbc02ec
Fix weight remap for tresnet_v2_l
2023-04-21 09:05:04 -07:00
a08e5aed1d
More models w/ multi-weight support, moving to HF hub. Removing inplace_abn from all models including TResNet
2023-04-20 22:44:49 -07:00
2aabaef039
Merge pull request #1784 from huggingface/wip-voidbag-accumulate-grad
...
Accumulate gradients (adding to #1659 )
2023-04-20 08:15:28 -07:00
f4825a09ef
Merge pull request #212 from bryant1410/patch-1
...
Fix MultiEpochsDataLoader when there's no batching
2023-04-20 07:09:27 -07:00
4cd7fb88b2
clip gradients with update
2023-04-19 23:36:20 -07:00
df81d8d85b
Cleanup gradient accumulation, fix a few issues, a few other small cleanups in related code.
2023-04-19 23:11:00 -07:00
ab7ca62a6e
Merge branch 'main' of github.com:rwightman/pytorch-image-models into wip-voidbag-accumulate-grad
2023-04-19 11:08:12 -07:00
34df125be6
cait, volo, xvit hub weights
2023-04-14 10:13:13 -07:00
f6d5767551
cspnet models on HF hub w/ multi-weight support
2023-04-12 14:02:38 -07:00
aef6e562e4
Add onnx utils and export code, tweak padding and conv2d_same for better dynamic export with recent PyTorch
2023-04-11 17:03:57 -07:00
80b247d843
Update swin_v2 attn_mask buffer change in #1790 to apply to updated checkpoints in hub
2023-04-11 14:40:32 -07:00
1a1aca0cee
Merge pull request #1761 from huggingface/patch_drop_refactor
...
Implement patch dropout for eva / vision_transformer, refactor dropout args
2023-04-11 14:37:36 -07:00
c0670822d2
Small factory handling fix for pretrained tag vs cfg
2023-04-11 07:42:13 -07:00
2f25f73b90
Missed a fused_attn update in relpos vit
2023-04-10 23:30:50 -07:00
0b65b5c0ac
Add finalized eva CLIP weights pointing to remapped timm hub models
2023-04-10 23:13:12 -07:00
965d0a2d36
fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights.
2023-04-10 12:04:33 -07:00
4d135421a3
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
c76818a592
skip attention mask buffers
...
Allows more flexibility in the resolutions accepted by SwinV2.
2023-04-07 18:50:02 +02:00
1bb3989b61
Improve kwarg passthrough for swin, vit, deit, beit, eva
2023-04-05 21:37:16 -07:00
35c94b836c
Update warning message for deprecated model names
2023-04-05 17:24:17 -07:00
9eaab795c2
Add some vit model deprecations
2023-04-05 17:21:03 -07:00
b17abd35b2
Version 0.8.19dev0
2023-04-05 16:37:16 -07:00
abff3f12ec
Wrong pool_size for 288 ft
2023-04-05 16:07:51 -07:00
356309959c
ResNet models on HF hub, multi-weight support, add torchvision v2 weights, new 12k pretrained and fine-tuned timm anti-aliased weights
2023-04-05 14:19:42 -07:00
7501972cd6
Version 0.8.18dev0
2023-03-31 16:51:26 -07:00
beef7f0a22
Add ImageNet-12k intermediate fine-tunes of convnext base & large CLIP models, add first 1k fine-tune of xxlarge
2023-03-31 16:45:01 -07:00
9aa1133bd2
Fix #1750 , uncomment weight that exists on HF hub, add FIXME to 3 others that are still on local storage
2023-03-31 14:49:30 -07:00
7326470514
Merge pull request #1746 from huggingface/eva02
...
Adding EVA02 weights and model defs
2023-03-31 12:17:00 -07:00
adeb9de7c6
Mismatch in eva pretrained_cfg vs model for one of the clip variants
2023-03-31 10:30:30 -07:00
0737bd3ec8
eva02 non-CLIP weights on HF hub, add initial eva02 clip model configs w/ postnorm variant & attn LN
2023-03-30 23:43:59 -07:00
ac67098147
Add final attr for fast_attn on beit / eva
2023-03-28 08:40:40 -07:00
1885bdc431
Merge pull request #1745 from huggingface/mw-mlp_mixer
...
MLP-Mixer multi-weight support, HF hub push
2023-03-28 07:55:17 -07:00
e9f427b953
Add hf hub entries for mlp_mixer
2023-03-27 22:50:43 -07:00
cff81deb78
multi-weight and hf hub for deit / deit3
2023-03-27 22:47:16 -07:00
3863d63516
Adding EVA02 weights and model defs, move beit based eva_giant to same eva.py file. Cleanup rotary pos, add lang oriented freq bands to be compat with eva design choice. Fix #1738
2023-03-27 17:16:07 -07:00
b12060996c
MLP-Mixer multi-weight support, hf hub push
2023-03-27 16:42:13 -07:00
d196fa536d
Fix last min torchscript regression in nfnet changes
2023-03-24 00:10:17 -07:00
33ada0cbca
Add group_matcher to focalnet for proper layer-wise LR decay
2023-03-23 23:21:49 -07:00
b271dc0e16
NFNet multi-weight support + HF hub push
2023-03-23 23:20:38 -07:00
a089bfba2d
Version 0.8.17dev0
2023-03-22 15:40:23 -07:00
dbd33e4b62
Update crop settings for new rexnet weights
2023-03-22 15:39:49 -07:00
da6bdd4560
Update resnetv2.py for multi-weight and HF hub weights
2023-03-22 15:38:04 -07:00
b3e816d6d7
Improve filtering behaviour for tag + non-tagged model wildcard consistency.
2023-03-22 10:21:22 -07:00
7aba64ebdb
Add update byobnet.py w/ models pushed to HF hub
2023-03-22 10:00:00 -07:00
e7ef8335bf
regnet.py multi-weight conversion, new ImageNet-12k pretrain/ft from timm for y_120 and y_160, also new tv v2, swag, & seer weights for push to Hf hub.
2023-03-21 15:51:49 -07:00
c78319adce
Add ImageNet-12k ReXNet-R 200 & 300 weights, and push existing ReXNet models to HF hub. Dilation support added to rexnet
2023-03-20 13:48:17 -07:00
8db20dc240
Fix #1726 , dropout not used in NormMlpClassifierHead. Make dropout more consistent across both classifier heads (nn.Dropout)
2023-03-20 09:37:05 -07:00
041de79f9e
Fix numel use in helpers for checkpoint remap
2023-03-20 09:36:48 -07:00
49b9c3be80
Include pretrained tag in deprecated mapping warning
2023-03-19 21:21:19 -07:00
fafac3317c
Version 0.8.16dev0
2023-03-18 15:09:20 -07:00
9fcfb8bcc1
Add Microsoft FocalNet specific ('ms') ImageNet-22k classifier layout
2023-03-18 14:57:34 -07:00
572f05096a
Swin and FocalNet weights on HF hub. Add model deprecation functionality w/ some registry tweaks.
2023-03-18 14:55:09 -07:00
5aebad3fbc
return_map back to out_map for _feature helpers
2023-03-16 14:50:55 -07:00
acfd85ad68
All swin models support spatial output, add output_fmt to v1/v2 and use ClassifierHead.
...
* update ClassifierHead to allow different input format
* add output format support to patch embed
* fix some flatten issues for a few conv head models
* add Format enum and helpers for tensor format (layout) choices
2023-03-15 23:21:51 -07:00
c30a160d3e
Merge remote-tracking branch 'origin/main' into focalnet_and_swin_refactor
2023-03-15 15:58:39 -07:00
ad94d737b7
Add support to ConvNextBlock for downsample and channel expansion to improve stand alone use. Fix #1699
2023-03-13 14:06:24 -07:00
3a636eee71
Fix #1713 missed assignement in 3-aug level fn, fix few other minor lint complaints in auto_augment.py
2023-03-11 14:32:23 -08:00
992bf7c3d4
chore: Modify the MobileVitV2Block to be coreml exportable
...
based on is_exportable() set variable controlling behaviour of the block
CoreMLTools support im2col from 6.2 version, unfortunately col2im
is still not supported.
Tested with exporting to ONNX, Torchscript, CoreML, and TVM.
2023-03-03 09:38:24 +01:00
4b8cfa6c0a
Add convnext_xxlarge CLIP image tower weights, version 0.8.15dev0
2023-02-26 21:51:48 -08:00
f9b56a1bfa
Version 0.8.14dev0
2023-02-26 13:38:51 -08:00
1c13ef7b46
Add default norm_eps=1e-5 for convnext_xxlarge, improve kwarg merging for all convnext models
2023-02-26 12:11:49 -08:00
a5b01ec04e
Add type annotations to _registry.py
...
Description
Add type annotations to _registry.py so that they will pass mypy
--strict.
Comment
I was reading the code and felt that this module would be easier to
understand with type annotations. Therefore, I went ahead and added the
annotations.
The idea with this PR is to start small to see if we can align on _how_
to annotate types. I've seen people in the past disagree on how strictly
to annotate the code base, so before spending too much time on this, I
wanted to check if you agree, Ross.
Most of the added types should be straightforward. Some notes on the
non-trivial changes:
- I made no assumption about the fn passed to register_model, but maybe
the type could be stricter. Are all models nn.Modules?
- If I'm not mistaken, the type hint for get_arch_name was incorrect
- I had to add a # type: ignore to model.__all__ = ...
- I made some minor code changes to list_models to facilitate the
typing. I think the changes should not affect the logic of the function.
- I removed list from list(sorted(...)) because sorted returns always a
list.
2023-02-22 09:19:30 -08:00
47f1de9bec
Version bump
2023-02-20 10:17:10 -08:00
4d9c3ae2fb
Add laion2b 320x320 ConvNeXt-Large CLIP weights
2023-02-18 16:34:03 -08:00
d0b45c9b4d
Make safetensor import option for now. Improve avg/clean checkpoints ext handling a bit (more consistent).
2023-02-18 16:06:42 -08:00
947c1d757a
Merge branch 'main' into focalnet_and_swin_refactor
2023-02-17 16:28:52 -08:00
cf324ea38f
Fix grad checkpointing in focalnet
2023-02-17 16:26:26 -08:00
848d200767
Overhaul FocalNet implementation
2023-02-17 16:24:59 -08:00
7266c5c716
Merge branch 'main' into focalnet_and_swin_refactor
2023-02-17 09:20:14 -08:00
7d9e321b76
Improve tracing of window attn models with simpler reshape logic
2023-02-17 07:59:06 -08:00
2e38d53dca
Remove dead line
2023-02-16 16:57:42 -08:00
f77c04ff36
Torchscript fixes/hacks for rms_norm, refactor ParallelScalingBlock with manual combination of input projections, closer paper match
2023-02-16 16:57:42 -08:00
122621daef
Add Final annotation to attn_fas to avoid symbol lookup of new scaled_dot_product_attn fn on old PyTorch in jit
2023-02-16 16:57:42 -08:00
621e1b2182
Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.
2023-02-16 16:57:42 -08:00
a3d528524a
Version 0.8.12dev0
2023-02-16 16:27:29 -08:00
a09d403c24
changed warning to info
2023-02-16 16:20:31 -08:00
8470e29541
Add support to load safetensors weights
2023-02-16 16:20:31 -08:00
f35d6ea57b
Add multi-tensor (foreach) version of Lion in style of upcoming PyTorch 2.0 optimizers
2023-02-16 15:48:00 -08:00
709d5e0d9d
Add Lion optimizer
2023-02-14 23:55:05 -08:00
624266148d
Remove unused imports from _hub helpers
2023-02-09 17:47:26 -08:00
2cfff0581b
Add grad_checkpointing support to features_only, test in EfficientDet.
2023-02-09 17:45:40 -08:00
45af496197
Version 0.8.11dev0
2023-02-08 08:29:29 -08:00
9c14654a0d
Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg
2023-02-08 08:29:20 -08:00
497be8343c
Update README and version
2023-02-06 23:43:14 -08:00
0d33127df2
Add 384x384 convnext_large_mlp laion2b fine-tune on in1k
2023-02-06 22:01:04 -08:00
7a0bd095cb
Update model prune loader to use pkgutil
2023-02-06 17:45:16 -08:00
0f2803de7a
Move ImageNet metadata (aka info) files to timm/data/_info. Add helper classes to make info available for labelling. Update inference.py for first use.
2023-02-06 17:45:03 -08:00
7f29a46d44
Add gradient accumulation option to train.py
...
option: iters-to-accum(iterations to accmulate)
Gradient accumulation improves training performance(samples/s).
It can reduce the number of parameter sharing between each node.
This option can be helpful when network is bottleneck.
Signed-off-by: Taeksang Kim <voidbag@puzzle-ai.com>
2023-02-06 09:24:48 +09:00
7a13be67a5
Update version.py
2023-02-05 10:06:15 -08:00
13acac8c5e
Update head metadata for effformerv2
2023-02-04 23:11:51 -08:00
8682528096
Add first conv metadata for efficientformer_v2
2023-02-04 23:02:02 -08:00
72fba669a8
is_scripting() guard on checkpoint_seq
2023-02-04 14:21:49 -08:00
95ec255f7f
Finish timm mode api for efficientformer_v2, add grad checkpointing support to both efficientformers
2023-02-03 21:21:23 -08:00
9d03c6f526
Merge remote-tracking branch 'origin/main' into levit_efficientformer_redux
2023-02-03 14:47:01 -08:00
086bd55a94
Add EfficientFormer-V2, refactor EfficientFormer and Levit for more uniformity across the 3 related arch. Add features_out support to levit conv models and efficientformer_v2. All weights on hub.
2023-02-03 14:12:29 -08:00
2cb2699dc8
Apply fix from #1649 to main
2023-02-03 11:28:57 -08:00
b3042081b4
Add laion -> in1k fine-tuned base and large_mlp weights for convnext
2023-02-03 10:58:02 -08:00
316bdf8955
Add mlp head support for convnext_large, add laion2b CLIP weights, prep fine-tuned weight tags
2023-02-01 08:27:02 -08:00
6f28b562c6
Factor NormMlpClassifierHead from MaxxViT and use across MaxxViT / ConvNeXt / DaViT, refactor some type hints & comments
2023-01-27 14:57:01 -08:00
9a53c3f727
Finalize DaViT, some formatting and modelling simplifications (separate PatchEmbed to Stem + Downsample, weights on HF hub.
2023-01-27 13:54:04 -08:00
fb717056da
Merge remote-tracking branch 'upstream/main'
2023-01-26 10:49:15 -08:00
14b84e8895
📝 update docstrings
2023-01-26 00:49:44 -05:00
f0dc8a8267
📝 update docstrings for create_model
2023-01-25 21:10:41 -05:00
2bbc26dd82
version 0.8.8dev0
2023-01-25 18:02:48 -08:00
64667bfa0e
Add 'gigantic' vit clip variant for feature extraction and future fine-tuning
2023-01-25 18:02:10 -08:00
c2822568ec
Update version to 0.8.7dev0
2023-01-20 15:01:10 -08:00
36989cfae4
Factor out readme generation in hub helper, add more readme fields
2023-01-20 14:49:40 -08:00
32f252381d
Change order of checkpoitn filtering fn application in builder, try dict, model variant first
2023-01-20 14:48:54 -08:00
e9f1376cde
Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn
2023-01-20 14:47:55 -08:00
bed350f5e5
Push all MaxxViT weights to HF hub, cleanup impl, add feature map extraction support and prompote to 'std' architecture. Fix norm head for proper embedding / feat map output. Add new in12k + ft 1k weights.
2023-01-20 14:45:25 -08:00
ca38e1e73f
Update ClassifierHead module, add reset() method, update in_chs -> in_features for consistency
2023-01-20 14:44:05 -08:00
8ab573cd26
Add convnext_tiny and convnext_small 384x384 fine-tunes of in12k weights, fix pool size for laion CLIP convnext weights
2023-01-20 14:40:16 -08:00
81ca323751
Davit update formatting and fix grad checkpointing ( #7 )
...
fixed head to gap->norm->fc as per convnext, along with option for norm->gap->fc
failed tests due to clip convnext models, davit tests passed
2023-01-15 14:34:56 -08:00
e9aac412de
Correct mean/std for CLIP convnexts
2023-01-14 22:53:56 -08:00
42bd8f7bcb
Add convnext_base CLIP image tower weights for fine-tuning / features
2023-01-14 21:16:29 -08:00
e520553e3e
Update batchnorm freezing to handle NormAct variants, Add GroupNorm1Act, update BatchNormAct2d tracing change from PyTorch
2023-01-12 16:55:47 -08:00
a2c14c2064
Add tiny/small in12k pretrained and fine-tuned ConvNeXt models
2023-01-11 14:50:39 -08:00
c061d5e401
Allow using class_map functionality w/ IterableDataset (TFDS/WDS) to remap class labels
2023-01-09 16:28:47 -08:00
01fdf44438
Initial focalnet import, more refactoring needed for timm.
2023-01-09 16:18:19 -08:00
01aea8c1bf
Version 0.8.6dev0
2023-01-09 13:38:31 -08:00
2e83bba142
Revert head norm changes to ConvNeXt as it broke some downstream use, alternate workaround for fcmae weights
2023-01-09 13:37:40 -08:00
1825b5e314
maxxvit type
2023-01-09 08:57:31 -08:00
5078b28f8a
More kwarg handling tweaks, maxvit_base_rw def added
2023-01-09 08:57:31 -08:00
c0d7388a1b
Improving kwarg merging in more models
2023-01-09 08:57:31 -08:00
ae9153052f
Update version.py
2023-01-06 17:17:35 -08:00
60ebb6cefa
Re-order vit pretrained entries for more sensible default weights (no .tag specified)
2023-01-06 16:12:33 -08:00
e861b74cf8
Pass through --model-kwargs (and --opt-kwargs for train) from command line through to model __init__. Update some models to improve arg overlay. Cleanup along the way.
2023-01-06 16:12:33 -08:00
add3fb864e
Working on improved model card template for push_to_hf_hub
2023-01-06 16:12:33 -08:00
dd0bb327e9
Update version.py
...
Ver 0.8.4dev0
2023-01-05 07:55:18 -08:00
6e5553da5f
Add ConvNeXt-V2 support (model additions and weights) ( #1614 )
...
* Add ConvNeXt-V2 support (model additions and weights)
* ConvNeXt-V2 weights on HF Hub, tweaking some tests
* Update README, fixing convnextv2 tests
2023-01-05 07:53:32 -08:00
6902c48a5f
Fix ResNet based models to work w/ norm layers w/o affine params. Reformat long arg lists into vertical form.
2022-12-29 16:32:26 -08:00
d5aa17e415
Remove print from auto_augment
2022-12-28 17:11:35 -08:00
7c846d9970
Better vmap compat across recent torch versions
2022-12-24 14:37:04 -08:00
4e24f75289
Merge pull request #1593 from rwightman/multi-weight_effnet_convnext
...
Update efficientnet.py and convnext.py to multi-weight, add new 12k pretrained weights
2022-12-23 10:09:08 -08:00
8ece53e194
Switch BEiT to HF hub weights
2022-12-22 21:43:04 -08:00
d1bfa9a000
Support HF datasets and TFSD w/ a sub-path by fixing split, fix #1598 ... add class mapping support to HF datasets in case class label isn't in info.
2022-12-22 21:34:13 -08:00
e2fc43bc63
Version 0.8.2dev0
2022-12-22 17:34:09 -08:00
9a51e4ea2e
Add FlexiViT models and weights, refactoring, push more weights
...
* push all vision_transformer*.py weights to HF hub
* finalize more pretrained tags for pushed weights
* refactor pos_embed files and module locations, move some pos embed modules to layers
* tweak hf hub helpers to aid bulk uploading and updating
2022-12-22 17:23:09 -08:00
10b3f696b4
Davit std ( #6 )
...
Separate patch_embed module
2022-12-16 21:50:28 -08:00
Ross Wightman
Ross Wightman
Marco Forte
Piotr Sebastian Kluska
Benjamin Bossan
testbot
Taeksang Kim
Fredo Guan
nateraw