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

• 36a5648208 Merge branch 'master' of https://github.com/gcucurull/pytorch-image-models into gcucurull-master Ross Wightman 2021-03-14 12:01:21 -0700
• dfae015c5d Move modelindex files into doc tree, add headings to model templates. Tweak a few details. Ross Wightman 2021-03-14 12:00:11 -0700
• 8936356139 Add results to model-index #494 Marcin Kardas 2021-03-12 18:38:10 +0000
• 4d26eed4d4 fix typo in urls Guillem Cucurull 2021-03-12 12:53:43 +0000
• 3f6501c1ad Add short comment Guillem Cucurull 2021-03-11 17:09:32 +0000
• 9e74125276 Model index files and script to generate it Guillem Cucurull 2021-03-11 16:52:13 +0000
• d76483b468 Deployed 5c7d298 with MkDocs version: 1.1.2 Ross Wightman 2021-03-10 10:29:34 -0800
• 5c7d298234 Update README.md, documentation, add TOC, sponsors, and links to timmdocs and paperswithcode Ross Wightman 2021-03-10 10:23:51 -0800
• f043c02c5a Fix issue in feature extraction when using a local checkpoint #489 ryanking13 2021-03-10 15:10:03 +0900
• f1f332fee5
  Update README.md Ross Wightman 2021-03-07 16:43:52 -0800
• 5b28ef4100
  Merge pull request #475 from rwightman/pre-release/0.4.5 v0.4.5 Ross Wightman 2021-03-07 16:18:31 -0800
• f57db99101 Update README, fix iabn pip version print. #475 Ross Wightman 2021-03-07 16:16:54 -0800
• 7ef7788ee9 Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk() Ross Wightman 2021-02-23 13:15:52 -0800
• 317ea3e599 Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features for simplicty. Update tests for pytorch 1.8. 0.4.5 version bump. Ross Wightman 2021-03-06 12:48:06 -0800
• 4445eaa470 Add img_size to benchmark output Ross Wightman 2021-03-05 16:48:31 -0800
• 5fcdd4b822
  Merge pull request #459 from onatyap/patch-2 Ross Wightman 2021-03-05 10:27:47 -0800
• 17cdee7354 Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model. Ross Wightman 2021-03-01 16:53:32 -0800
• 95feb1da41 Update results csvs, run with PyTorch 1.7.1 cuda 10.2, some differences from prev run with older PT ver. Ross Wightman 2021-02-28 17:43:22 -0800
• 0706d05d52 Benchmark models listed in txt file. Add more hybrid vit variants for testing Ross Wightman 2021-02-28 16:00:33 -0800
• 3b95fa4248
  corrected typo in feature_extraction.md #459 Onat Yapici 2021-02-28 16:25:00 +0300
• d8131d5d47 fixing master bug on hardcoded osnet architecture #434 szingaro 2021-02-25 12:58:01 +0100
• 7a2076ae04 Merge branch 'master' of github.com:szingaro/pytorch-image-models szingaro 2021-02-25 11:13:56 +0100
• 203219f906 editing hybrid backbone for osnet specific architecture | to be generalized szingaro 2021-02-25 11:13:45 +0100
• d79d372be4
  Merge pull request #2 from rwightman/master szingaro 2021-02-25 10:47:10 +0100
• 2db2d87ff7 Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only. Ross Wightman 2021-02-23 17:31:42 -0800
• de97be9146 Spell out diff between my small and deit small vit models. Ross Wightman 2021-02-23 16:22:55 -0800
• f0ffdf89b3 Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing. Ross Wightman 2021-02-23 15:54:55 -0800
• 0e16d4e9fb Add benchmark.py script, and update optimizer factory to be more friendly to use outside of argparse interface. Ross Wightman 2021-02-23 13:26:42 -0800
• 4bc103f504 Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk() Ross Wightman 2021-02-23 13:15:52 -0800
• eac13f7821
  fix typo #447 Tsubota 2021-02-22 23:35:38 +0900
• 48371a33b1
  Create FUNDING.yml Ross Wightman 2021-02-18 16:12:53 -0800
• da4839530c Fix test model filter to include dm_ variants that break GitHub CI limits Ross Wightman 2021-02-18 13:43:04 -0800
• 8563609b28 Update notes in ScaledStdConv impl Ross Wightman 2021-02-18 12:44:08 -0800
• 678ba4e0a2 Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config. Ross Wightman 2021-02-18 12:28:46 -0800
• aa6daf20af Add dependency everywhere #440 Sylvain Gugger 2021-02-18 09:20:01 -0500
• 614b73bd35 Add dependency Sylvain Gugger 2021-02-18 09:11:23 -0500
• f269f2d9d5 Consistently use hf_model_id Sylvain Gugger 2021-02-18 09:09:48 -0500
• 482ab548dc
  Merge branch 'master' into master Sylvain Gugger 2021-02-18 09:05:23 -0500
• b506f7bc36 Add a second example model Julien Chaumond 2021-02-18 12:22:12 +0100
• dd12f9f2a5 Change default weights filename + default branch is main Julien Chaumond 2021-02-18 11:51:50 +0100
• 4ea5931964
  Merge pull request #437 from rwightman/agc v0.1-dnf-weights Ross Wightman 2021-02-16 10:27:58 -0800
• 361fd0fc40
  Update README.md #437 Ross Wightman 2021-02-16 10:27:41 -0800
• 9de2ec5e44 Update README for AGC and bump version to 0.4.4 Ross Wightman 2021-02-16 09:12:23 -0800
• 01653db104 Missed clip-mode arg for repo train script Ross Wightman 2021-02-15 23:27:16 -0800
• 4f49b94311 Initial AGC impl. Still testing. Ross Wightman 2021-02-15 23:22:44 -0800
• 7987f0c83d up szingaro 2021-02-15 19:55:48 +0100
• 9dec7feef9
  Merge pull request #1 from rwightman/master szingaro 2021-02-15 19:25:25 +0100
• 5f9aff395c Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing. Ross Wightman 2021-02-13 16:58:51 -0800
• 4df513c68f
  Merge pull request #427 from rwightman/nfnet Ross Wightman 2021-02-12 22:08:03 -0800
• d86dbe45c2 Update README.md and few more comments #427 Ross Wightman 2021-02-12 22:07:18 -0800
• 0d253e2c5e Fix issue with nfnet tests, bit more cleanup. Ross Wightman 2021-02-12 21:05:41 -0800
• cb06c7a910 Add NFNet-F models and tweak existing NF models. Ross Wightman 2021-02-12 18:28:56 -0800
• 607f9149b1
  Update README.md Ross Wightman 2021-02-11 22:06:06 -0800
• 8c270ed7bf
  Merge pull request #1 from sgugger/add_hf_hub Sylvain Gugger 2021-02-11 17:50:37 -0500
• e4de077021 Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288). Ross Wightman 2021-02-11 13:15:20 -0800
• 5482d2e501 Actually load the model Sylvain Gugger 2021-02-11 11:11:26 -0500
• 7dafa71c0e Use the model hub config Sylvain Gugger 2021-02-11 10:47:30 -0500
• 4d0b5feed0 Make `create_model` work from a checkpoint Sylvain Gugger 2021-02-11 10:34:15 -0500
• 9857e12c0c Be more opt-in Sylvain Gugger 2021-02-11 09:33:12 -0500
• ebe69dd4d3 PoC for using HF model hub Sylvain Gugger 2021-02-11 09:13:49 -0500
• a00011188e PoC to add HF hub #425 Sylvain Gugger 2021-02-11 09:05:15 -0500
• 550a478fa5 Deployed d8e6920 with MkDocs version: 1.1.2 Ross Wightman 2021-02-10 23:29:22 -0800
• d8e69206be
  Merge pull request #419 from rwightman/byob_vgg_models Ross Wightman 2021-02-10 15:44:09 -0800
• ca9b078ac7 Update README.md and docs. Version bumped to 0.4.3 #419 Ross Wightman 2021-02-10 14:46:07 -0800
• 6853b07bbd Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments. Ross Wightman 2021-02-10 14:40:29 -0800
• 0356e773f5 Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately. Ross Wightman 2021-02-10 14:31:18 -0800
• b9bd960a03
  Merge pull request #421 from aboutmedicine/master Ross Wightman 2021-02-10 08:11:49 -0800
• 94ca140b67 update collections.abc import #421 Reuben 2021-02-10 23:54:35 +1100
• db6128db0f
  Merge pull request #418 from kecsap/master Ross Wightman 2021-02-09 20:55:55 -0800
• b4e216e377 Fix a few small things. Ross Wightman 2021-02-09 17:33:43 -0800
• dc85e5a237 Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models. Ross Wightman 2021-02-09 16:21:47 -0800
• 1bcc69e0ad Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354. Ross Wightman 2021-02-09 16:00:19 -0800
• 9811e229f7 Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models. Ross Wightman 2021-02-09 15:58:39 -0800
• 5114c214fc Change the Python interpreter to Python 3.x in the scripts #418 Csaba Kertesz 2021-02-09 21:20:28 +0200
• aaa715b1e9
  Update README.md v0.1-repvgg-weights v0.1-ger-weights Ross Wightman 2021-02-08 12:04:48 -0800
• a7f95818e4
  Merge pull request #413 from rwightman/eca-weights Ross Wightman 2021-02-08 12:03:19 -0800
• a39c3ee216
  Merge branch 'master' into eca-weights #413 Ross Wightman 2021-02-08 11:52:31 -0800
• e9d6fe293c Update README for new weights. Version 0.4.2 Ross Wightman 2021-02-08 11:51:16 -0800
• 666de85cf1 Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414 Ross Wightman 2021-02-07 22:10:18 -0800
• 3b57490a63 Fix some half removed resnet model defs, pooling for ecaresnet269d Ross Wightman 2021-02-07 22:09:25 -0800
• 2a8c4dc63b Add validation script update for using test_input_size in model default_cfgs Ross Wightman 2021-02-07 21:35:50 -0800
• 68a4144882 Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg. Ross Wightman 2021-02-06 16:30:02 -0800
• 3a7aa95f7e
  Update README.md Ross Wightman 2021-02-05 07:39:21 -0800
• b9843f954b
  Merge pull request #282 from tigert1998/patch-1 Ross Wightman 2021-02-04 12:18:40 -0800
• ea36a78cff
  Merge pull request #401 from hwangdeyu/deyu/add_HardSwishJitAutoFn_operator Ross Wightman 2021-02-04 12:18:19 -0800
• 7a4be5c035 add operator HardSwishJitAutoFn export to onnx #401 hwangdeyu 2021-02-02 18:02:41 +0800
• 4203efa36d Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py. Ross Wightman 2021-01-31 20:14:51 -0800
• 99b82ae5ab
  Merge pull request #389 from rwightman/norm_free_models Ross Wightman 2021-01-31 12:47:47 -0800
• 499790e117 fix: torchscript #382 iyaja 2021-01-31 14:30:56 +0530
• 225d45afac fix: resnet18 iyaja 2021-01-31 13:56:13 +0530
• f0e65e37b7 Fix NF-ResNet101 model defs #389 Ross Wightman 2021-01-30 23:26:19 -0800
• 2c988c3b6e Update README.md for NF-nets, bump version to 0.4.1 for merge Ross Wightman 2021-01-30 23:19:45 -0800
• ff1445952a fix: model name Ajay Uppili Arasanipalai 2021-01-31 12:23:53 +0530
• 368834ab3c refactor: use fewer triplet models Ajay Uppili Arasanipalai 2021-01-31 11:32:52 +0530
• 2de54d174a Fix pool size defs for NFNet models, add a comment. Ross Wightman 2021-01-30 18:02:33 -0800
• 90980de4a9 Fix up a few details in NFResNet models, managed stable training. Add support for gamma gain to be applied in activation or ScaleStdConv. Some tweaks to ScaledStdConv. Ross Wightman 2021-01-30 16:32:07 -0800
• 5a8e1e643e Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring. Ross Wightman 2021-01-27 22:06:57 -0800
• 9a38416fbd
  Merge pull request #323 from rwightman/imagenet21k_datasets_more Ross Wightman 2021-01-25 13:31:15 -0800
• 745bc5f723 Mention 21k ViT weights in README.md #323 Ross Wightman 2021-01-25 12:03:13 -0800
• 6306aa79e9
  Merge branch 'master' into imagenet21k_datasets_more Ross Wightman 2021-01-25 12:26:05 -0800