Commit Graph

Select branches

Hide Pull Requests

0.5.x

0.6.x

attn_update

bits_and_tpu

cleanup_xla_model_fixes

clip_laion2b

convnext_and_copyright

convnextv2

dataset_info

edgenext_csp_and_more

efficientnet_attn

eva

fix_tests

fix_window_trace

fixes-syncbn_pretrain_cfg_resolve

fixes_bce_regnet

focalnet_and_swin_refactor

freeze_norm_revisit

gh-pages

hf_hub_revisit

levit_efficientformer_redux

main

maxxvit_hub

more_attn

more_datasets

more_vit

multi-weight

multi-weight_effnet_convnext

norm_mlp_classifier

norm_norm_norm

parse_kwargs

parse_kwargs2

perceiver

refactor-imports

scaling_vit

script_cleanup

swin_v2

update-test-pytorch

vit_and_bit_test_fixes

vit_relpos_refactor

xsepconv

#1

#1007

#101

#1012

#1014

#1034

#1037

#105

#1055

#1056

#1056

#1058

#1061

#1063

#1063

#1069

#1083

#1091

#1094

#1105

#1112

#1113

#115

#1150

#117

#1187

#1190

#1194

#12

#1208

#1210

#1210

#1212

#1213

#1213

#122

#1222

#1222

#1229

#123

#1230

#1233

#1239

#1245

#1249

#125

#1251

#1253

#1253

#1256

#1259

#1265

#1266

#1270

#1271

#1271

#1273

#1274

#1276

#1277

#1294

#13

#1317

#132

#1322

#1327

#1330

#1330

#1336

#1340

#1345

#1349

#1351

#1354

#136

#1363

#1365

#137

#1381

#1383

#1385

#140

#141

#1414

#1415

#142

#1420

#143

#1439

#1439

#145

#146

#1467

#1471

#1473

#1476

#1479

#148

#1483

#1493

#1494

#1498

#150

#1500

#1502

#1520

#1522

#1525

#1527

#1532

#1538

#154

#1545

#1547

#155

#1552

#1553

#1553

#156

#1562

#1564

#1565

#1575

#1578

#1578

#1581

#1582

#1583

#1586

#1590

#1590

#1592

#1593

#16

#1606

#1612

#1614

#1617

#1617

#1621

#1622

#1624

#1627

#1628

#1628

#163

#1630

#1633

#1641

#1643

#1643

#1645

#1647

#1647

#1649

#1654

#1654

#1655

#1659

#1659

#1662

#1673

#1674

#1677

#1679

#1679

#1680

#1683

#1685

#1687

#1688

#1688

#175

#179

#183

#19

#191

#195

#199

#2

#208

#212

#212

#213

#213

#214

#216

#218

#227

#228

#23

#233

#237

#24

#240

#240

#244

#250

#255

#256

#263

#268

#282

#284

#286

#29

#290

#290

#297

#30

#300

#302

#31

#315

#32

#322

#323

#33

#334

#335

#35

#352

#367

#382

#389

#401

#413

#418

#419

#421

#425

#427

#429

#434

#437

#440

#447

#450

#459

#475

#489

#494

#497

#501

#502

#510

#52

#525

#528

#53

#533

#537

#542

#548

#550

#554

#555

#556

#561

#571

#580

#581

#595

#6

#603

#603

#609

#612

#613

#62

#625

#626

#636

#637

#645

#647

#65

#651

#652

#653

#659

#659

#66

#660

#668

#669

#679

#681

#685

#693

#7

#702

#714

#729

#731

#738

#74

#746

#747

#750

#768

#768

#771

#772

#800

#801

#804

#804

#805

#808

#812

#813

#816

#817

#82

#821

#828

#83

#841

#842

#853

#853

#858

#87

#874

#875

#876

#88

#880

#882

#891

#898

#910

#913

#914

#915

#933

#94

#95

#964

#967

#968

#986

#989

#99

#993

v0.1-attn-weights

v0.1-cadene

v0.1-coat-weights

v0.1-dnf-weights

v0.1-effv2-weights

v0.1-ger-weights

v0.1-hrnet

v0.1-mvit-weights

v0.1-pit-weights

v0.1-regnet

v0.1-repvgg-weights

v0.1-res2net

v0.1-resnest

v0.1-rexnet

v0.1-rs-weights

v0.1-rsb-weights

v0.1-selecsls

v0.1-tpu-weights

v0.1-tresnet

v0.1-vitjx

v0.1-vt3p-weights

v0.1-weights

v0.1-weights-maxx

v0.1-weights-morevit

v0.1-weights-swinv2

v0.1.1

v0.2.1

v0.3.3

v0.3.4

v0.4.12

v0.4.5

v0.4.9

v0.5.4

v0.6.11

v0.6.12

v0.6.5

v0.6.7

v0.8.10dev0

v0.8.13dev0

v0.8.2dev0

v0.8.6dev0

Mono Color

• a9917cb562
  Merge 1a934d2a5e into a5b01ec04e #1688 Benjamin Bossan 2023-02-23 13:19:29 +0000
• 1a934d2a5e Add pytest-cov, requirements-dev, pyproject.toml #1688 Benjamin Bossan 2023-02-23 14:11:03 +0100
• 7ce8aa25a9
  Merge 151fc8a14f into a5b01ec04e #1439 XiaXin 2023-02-23 10:47:21 +0100
• c872125c23
  Merge 14b84e8895 into a5b01ec04e #1643 Nathan Raw 2023-02-22 16:28:45 -0400
• 4de15f8469
  Merge a73d414c7e into a5b01ec04e #1647 Fredo Guan 2023-02-22 16:27:05 -0400
• 22329d045f
  Merge 8ed5ca81cc into a5b01ec04e #1679 Seyyed Hossein Hasanpour 2023-02-22 18:20:20 +0100
• a5b01ec04e Add type annotations to _registry.py main Benjamin Bossan 2023-02-22 14:14:01 +0100
• c9406ce608
  Some additions to the CONTRIBUTING guide (#1685) Benjamin Bossan 2023-02-22 17:24:26 +0100
• 76b306302c Add type annotations to _registry.py #1687 Benjamin Bossan 2023-02-22 14:14:01 +0100
• 22f0b44be1 [skip ci] empty commit to skip ci #1685 Benjamin Bossan 2023-02-22 11:32:57 +0100
• b995ca3c31 Some additions to the CONTRIBUTING guide Benjamin Bossan 2023-02-22 11:29:37 +0100
• c55c3a11d3
  Merge 7f29a46d44 into a32c4eff69 #1659 Taeksang Kim 2023-02-21 23:48:09 +0900
• 174444d096
  Merge 9191c294d3 into a32c4eff69 #1654 Kadir Nar 2023-02-21 08:14:34 +0100
• a32c4eff69
  Create CONTRIBUTING.md Ross Wightman 2023-02-20 17:13:10 -0800
• a0772f03e0
  Update README.md v0.8.13dev0 Ross Wightman 2023-02-20 10:26:09 -0800
• 47f1de9bec Version bump Ross Wightman 2023-02-20 10:13:44 -0800
• 11f7b589e5 Update setup.py for huggingface changes. Ross Wightman 2023-02-20 10:13:02 -0800
• 1c0cbe595f Version bump #1683 Ross Wightman 2023-02-20 10:13:44 -0800
• 47d8ffc629 Update setup.py for huggingface changes. Ross Wightman 2023-02-20 10:13:02 -0800
• cec5ddacd2
  Merge cf324ea38f into 4d9c3ae2fb #1628 Ross Wightman 2023-02-19 20:37:16 +0530
• a073986d85
  Merge 3491506fec into 4d9c3ae2fb #1553 Jérôme Rony 2023-02-19 21:34:38 +0800
• 4d9c3ae2fb Add laion2b 320x320 ConvNeXt-Large CLIP weights Ross Wightman 2023-02-18 16:34:03 -0800
• d0b45c9b4d Make safetensor import option for now. Improve avg/clean checkpoints ext handling a bit (more consistent). Ross Wightman 2023-02-18 16:06:42 -0800
• cf324ea38f Fix grad checkpointing in focalnet #1628 focalnet_and_swin_refactor Ross Wightman 2023-02-17 16:26:26 -0800
• 848d200767 Overhaul FocalNet implementation Ross Wightman 2023-02-17 16:24:59 -0800
• 7266c5c716 Merge branch 'main' into focalnet_and_swin_refactor Ross Wightman 2023-02-17 09:20:14 -0800
• 7d9e321b76 Improve tracing of window attn models with simpler reshape logic Ross Wightman 2023-02-16 23:46:52 -0800
• a3c6685e20
  Delete requirements-modelindex.txt Ross Wightman 2023-02-17 00:03:58 -0800
• 1ea0be1b17 Improve tracing of window attn models with simpler reshape logic #1680 fix_window_trace Ross Wightman 2023-02-16 23:46:52 -0800
• 022403ce0a Update README Ross Wightman 2023-02-16 17:20:27 -0800
• 2e38d53dca Remove dead line Ross Wightman 2023-02-15 15:38:41 -0800
• f77c04ff36 Torchscript fixes/hacks for rms_norm, refactor ParallelScalingBlock with manual combination of input projections, closer paper match Ross Wightman 2023-02-15 14:53:55 -0800
• 122621daef Add Final annotation to attn_fas to avoid symbol lookup of new scaled_dot_product_attn fn on old PyTorch in jit Ross Wightman 2023-02-15 08:53:50 -0800
• 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. Ross Wightman 2023-02-14 23:32:04 -0800
• a3d528524a Version 0.8.12dev0 Ross Wightman 2023-02-16 16:27:29 -0800
• a09d403c24 changed warning to info testbot 2023-02-16 11:27:27 +0100
• 8470e29541 Add support to load safetensors weights testbot 2023-02-16 10:47:04 +0100
• f35d6ea57b Add multi-tensor (foreach) version of Lion in style of upcoming PyTorch 2.0 optimizers Ross Wightman 2023-02-16 15:48:00 -0800
• 8ed5ca81cc add simplenet architecture #1679 seyyed hossein 2023-02-16 22:33:24 +0330
• 8d74dfcf90 changed warning to info #1677 testbot 2023-02-16 11:27:27 +0100
• 6f0c381ddd Add support to load safetensors weights testbot 2023-02-16 10:47:04 +0100
• e04400dc78 Remove dead line #1674 scaling_vit Ross Wightman 2023-02-15 15:38:41 -0800
• c53cf76fa3 Torchscript fixes/hacks for rms_norm, refactor ParallelScalingBlock with manual combination of input projections, closer paper match Ross Wightman 2023-02-15 14:53:55 -0800
• 49f248fa18 Merge branch 'main' into scaling_vit Ross Wightman 2023-02-15 09:26:28 -0800
• b6eb652924 Add Final annotation to attn_fas to avoid symbol lookup of new scaled_dot_product_attn fn on old PyTorch in jit Ross Wightman 2023-02-15 08:53:50 -0800
• 00001f91d0 fix bugs when tracing of swin_transformer #1673 root 2023-02-15 21:42:24 +0800
• 58d9f09c86
  Merge 16664ea31b into 709d5e0d9d #1330 swenkel 2023-02-15 14:22:52 +0100
• 709d5e0d9d Add Lion optimizer Ross Wightman 2023-02-14 23:55:05 -0800
• a9739258f4 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. Ross Wightman 2023-02-14 23:32:04 -0800
• a73d414c7e Update metaformers.py #1647 Fredo Guan 2023-02-10 03:33:41 -0800
• e2a9408dd0 Squashed commit of the following: Fredo Guan 2023-02-10 02:09:35 -0800
• 624266148d Remove unused imports from _hub helpers Ross Wightman 2023-02-09 17:47:26 -0800
• 2cfff0581b Add grad_checkpointing support to features_only, test in EfficientDet. Ross Wightman 2023-02-09 17:45:40 -0800
• 45af496197 Version 0.8.11dev0 Ross Wightman 2023-02-08 08:29:29 -0800
• 9c14654a0d Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg Ross Wightman 2023-02-08 07:56:19 -0800
• 1e0b347227 Fix README v0.8.10dev0 Ross Wightman 2023-02-06 23:46:26 -0800
• 497be8343c Update README and version Ross Wightman 2023-02-06 23:43:14 -0800
• 0d33127df2 Add 384x384 convnext_large_mlp laion2b fine-tune on in1k Ross Wightman 2023-02-06 22:01:04 -0800
• 88a5b8491d
  Merge pull request #1662 from rwightman/dataset_info Ross Wightman 2023-02-06 20:23:06 -0800
• 7a0bd095cb Update model prune loader to use pkgutil #1662 dataset_info Ross Wightman 2023-02-06 17:45:16 -0800
• 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. Ross Wightman 2023-02-06 17:41:07 -0800
• 89b0452171 Add PyTorch 1.13 inference benchmark numbers Ross Wightman 2023-02-06 09:09:04 -0800
• 7f29a46d44 Add gradient accumulation option to train.py #1659 Taeksang Kim 2023-02-06 07:32:21 +0900
• 7a13be67a5
  Update version.py Ross Wightman 2023-02-05 10:06:15 -0800
• 4b383e8ffe
  Merge pull request #1655 from rwightman/levit_efficientformer_redux Ross Wightman 2023-02-05 10:05:51 -0800
• 13acac8c5e Update head metadata for effformerv2 #1655 levit_efficientformer_redux Ross Wightman 2023-02-04 23:11:51 -0800
• 8682528096 Add first conv metadata for efficientformer_v2 Ross Wightman 2023-02-04 23:02:02 -0800
• 72fba669a8 is_scripting() guard on checkpoint_seq Ross Wightman 2023-02-04 14:21:49 -0800
• 95ec255f7f Finish timm mode api for efficientformer_v2, add grad checkpointing support to both efficientformers Ross Wightman 2023-02-03 21:21:23 -0800
• 9d03c6f526 Merge remote-tracking branch 'origin/main' into levit_efficientformer_redux Ross Wightman 2023-02-03 14:47:01 -0800
• 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. Ross Wightman 2023-02-03 14:12:29 -0800
• 2cb2699dc8 Apply fix from #1649 to main Ross Wightman 2023-02-03 11:28:57 -0800
• e0a5911072
  Merge pull request #1645 from rwightman/norm_mlp_classifier Ross Wightman 2023-02-03 11:00:58 -0800
• b3042081b4 Add laion -> in1k fine-tuned base and large_mlp weights for convnext #1645 norm_mlp_classifier Ross Wightman 2023-02-03 10:58:02 -0800
• 9191c294d3 Added Hugging Face demo application #1654 kadirnar 2023-02-03 13:48:47 +0300
• 9ecab46e18
  Merge pull request #1649 from leoentersthevoid/0.6.x 0.6.x Ross Wightman 2023-02-01 11:56:31 -0800
• b64acf5386
  Update tests.yml Ross Wightman 2023-02-01 10:45:53 -0800
• 316bdf8955 Add mlp head support for convnext_large, add laion2b CLIP weights, prep fine-tuned weight tags Ross Wightman 2023-02-01 08:27:02 -0800
• a4823653b9 fixed import in python 3.11.0 #1649 Claudiu Leoveanu 2023-02-01 12:17:15 +0200
• 0b1f84142f
  Merge branch 'rwightman:main' into metaformer_baselines_for_vision Fredo Guan 2023-01-31 22:17:06 -0800
• 5a19034a99 Update metaformers.py Fredo Guan 2023-01-31 22:15:08 -0800
• 5d9cb3b943 Update metaformers.py Fredo Guan 2023-01-31 19:25:47 -0800
• 1fd5f7672d Update metaformers.py Fredo Guan 2023-01-31 17:03:25 -0800
• 8f70650295 Update metaformers.py Fredo Guan 2023-01-31 16:45:38 -0800
• 01d02fb40f Update metaformers.py Fredo Guan 2023-01-31 16:43:19 -0800
• 7c04f6dc75 Update metaformers.py Fredo Guan 2023-01-28 15:09:12 -0800
• 6f28b562c6 Factor NormMlpClassifierHead from MaxxViT and use across MaxxViT / ConvNeXt / DaViT, refactor some type hints & comments Ross Wightman 2023-01-27 14:57:01 -0800
• 29fda20e6d Merge branch 'fffffgggg54-main' Ross Wightman 2023-01-27 13:55:17 -0800
• 9a53c3f727 Finalize DaViT, some formatting and modelling simplifications (separate PatchEmbed to Stem + Downsample, weights on HF hub. Ross Wightman 2023-01-27 13:54:04 -0800
• fb717056da Merge remote-tracking branch 'upstream/main' #1583 Fredo Guan 2023-01-26 10:49:15 -0800
• 14b84e8895 📝 update docstrings #1643 nateraw 2023-01-26 00:49:44 -0500
• f0dc8a8267 📝 update docstrings for create_model nateraw 2023-01-25 21:10:41 -0500
• 2bbc26dd82 version 0.8.8dev0 Ross Wightman 2023-01-25 18:02:48 -0800
• 64667bfa0e Add 'gigantic' vit clip variant for feature extraction and future fine-tuning Ross Wightman 2023-01-25 18:02:10 -0800
• 3aa31f537d
  Merge pull request #1641 from rwightman/maxxvit_hub Ross Wightman 2023-01-20 20:26:54 -0800
• 9983ed7721 xlarge maxvit killing the tests #1641 maxxvit_hub Ross Wightman 2023-01-20 16:16:20 -0800
• c2822568ec Update version to 0.8.7dev0 Ross Wightman 2023-01-20 15:01:10 -0800
• 0417a9dd81 Update README Ross Wightman 2023-01-20 15:00:49 -0800
• 36989cfae4 Factor out readme generation in hub helper, add more readme fields Ross Wightman 2023-01-20 14:49:40 -0800
• 32f252381d Change order of checkpoitn filtering fn application in builder, try dict, model variant first Ross Wightman 2023-01-20 14:48:54 -0800