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

• 16f1f77b41
  Add a test workflow for github actions Mike 2020-05-06 23:21:50 -0400
• a7ebe09029 Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given. Make small code refactoring Vyacheslav Shults 2020-05-06 09:54:03 +0300
• 4de2869e23 Merge branch 'master' of https://github.com/rwightman/pytorch-image-models into timm/code_refactoring #137 Vyacheslav Shults 2020-05-06 09:22:06 +0300
• 6cc11a8821
  Merge pull request #141 from Animatory/fix_HRNet Ross Wightman 2020-05-05 18:21:34 -0700
• f0eb021620 Replace all None by nn.Identity() in HRNet modules #141 Vyacheslav Shults 2020-05-05 21:09:35 +0300
• 3b72ebff51
  Merge pull request #140 from yoniaflalo/PR_MultiEpochsDataLoader Ross Wightman 2020-05-05 08:51:33 -0700
• a7f570c9b7 added MultiEpochsDataLoader #140 AFLALO, Jonathan Isaac 2020-05-05 14:32:10 +0300
• 2e085f9c6b Merge branch 'master' of https://github.com/rwightman/pytorch-image-models into timm/code_refactoring Vyacheslav Shults 2020-05-05 12:08:51 +0300
• 8d8677e03b Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too. Ross Wightman 2020-05-04 12:13:29 -0700
• bf865d32c2 Resolve merge conflicts Vyacheslav Shults 2020-05-04 19:52:20 +0300
• a1886346df Merge branch 'master' of https://github.com/rwightman/pytorch-image-models into timm/code_refactoring Vyacheslav Shults 2020-05-04 19:50:05 +0300
• 353a79aeba
  Update README.md Ross Wightman 2020-05-03 21:24:49 -0700
• c9b6f415ca Bump version for Pypi release Ross Wightman 2020-05-03 21:18:47 -0700
• 31f4c126ec Add EfficientNet pruned models to results files Ross Wightman 2020-05-03 20:15:11 -0700
• 375f3e5321 Fix pruned txt files not being installed during pip install Ross Wightman 2020-05-03 19:05:42 -0700
• 8ec554b82e
  Merge pull request #136 from yoniaflalo/adding_effnet_pruned Ross Wightman 2020-05-03 07:14:14 -0700
• 44ed0f85e8 Refactor imports and indents according to PEP. Add proposal for links to pretrained weights. Unify style of reset_classifier function. Replace None by nn.Identity() in torch modules (all empty classifiers and HRNet) Vyacheslav Shults 2020-05-03 15:56:15 +0300
• 9c15d57505 added efficientnet pruned weights #136 AFLALO, Jonathan Isaac 2020-05-03 09:29:45 +0300
• a4d20a1cb8
  Update README.md Ross Wightman 2020-05-01 19:22:35 -0700
• ea300709f0 Fix model create fn not passing num_classes through. Fix #135 Ross Wightman 2020-05-01 18:37:03 -0700
• 779cb0fcc0 Update results with new models Ross Wightman 2020-05-01 17:29:29 -0700
• 2c438c4e0d Merge branch 'master' of github.com:rwightman/pytorch-models Ross Wightman 2020-05-01 17:03:17 -0700
• 28739bb721 Merge branch 'VRandme-blur' Ross Wightman 2020-05-01 17:01:43 -0700
• 2681a8d618 Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop Ross Wightman 2020-05-01 17:00:21 -0700
• 9590f301a9 Merge branch 'blur' of https://github.com/VRandme/pytorch-image-models into VRandme-blur Ross Wightman 2020-05-01 15:19:57 -0700
• a5220ad3aa
  Merge pull request #125 from Separius/patch-1 Ross Wightman 2020-05-01 15:11:56 -0700
• 7a9942a75e Merge branch 'yoniaflalo-adding_ECA_resnet' Ross Wightman 2020-05-01 15:10:23 -0700
• 0834fbc01c Move pruned model adapt strings to separate txt files. A few minor formatting alignment tweaks. Ross Wightman 2020-05-01 15:09:20 -0700
• ba793f5c1c Merge branch 'adding_ECA_resnet' of https://github.com/yoniaflalo/pytorch-image-models into yoniaflalo-adding_ECA_resnet Ross Wightman 2020-04-29 16:43:02 -0700
• 07f19dd699 added eca resnet #132 AFLALO, Jonathan Isaac 2020-04-26 16:09:16 +0300
• 1d4ac1b165 Bump version for pypi release. Fix #130 Ross Wightman 2020-04-27 18:02:40 -0700
• be7c784d21 Small TResNet simplification, just use SelectAdaptivePool, don't notice any perf difference Ross Wightman 2020-04-27 17:50:19 -0700
• e3a98171b2 Remove some CRLF that made it into TResNet merge Ross Wightman 2020-04-27 13:23:41 -0700
• 0004f37d25 Some TResNet cleanup. * allow use of global pool arg, test-time-pooling * clean checkpoints to just contain state dict, add 448 res checkpoints * support DataParallel via lazy filter creation for JIT Downsample * some minor formatting (mostly alignment) preferences Ross Wightman 2020-04-27 13:21:05 -0700
• 64fe37d008 Remove old mean/std helper, rely fully on cmd line or default_cfg now. Fixes #126 Ross Wightman 2020-04-27 12:32:55 -0700
• 02a30411ad Replace fp16 with amp support for validate.py script Ross Wightman 2020-04-27 12:14:40 -0700
• e6f24e5578 Add 'momentum' optimizer (SGD w/o nesterov) for stable EfficientDet training defaults Ross Wightman 2020-04-25 19:42:13 -0700
• 20290b5b56
  fix typo in eca #125 Sepehr Sameni 2020-04-14 15:20:35 +0430
• ebf82b84ac
  Merge pull request #122 from mrT23/master v0.1-tresnet Ross Wightman 2020-04-12 18:23:46 -0700
• e15f979457
  Merge pull request #123 from aclex/mobilenetv3_fix_feature_extraction Ross Wightman 2020-04-12 18:17:13 -0700
• bdb165a8a4 Merge changes in feature extraction interface to MobileNetV3 #123 Alexey Chernov 2020-04-13 02:02:14 +0300
• 1c92755bb6 Merge branch 'master' of https://github.com/mrT23/pytorch-image-models talrid 2020-04-12 19:09:39 +0300
• 011a11d987 TResNet models talrid 2020-04-12 18:44:12 +0300
• 8a63c1add8 finalizing #122 talrid 2020-04-12 19:08:35 +0300
• 6209146738 TResNet models talrid 2020-04-12 18:44:12 +0300
• 98a7403ed4
  Merge pull request #1 from rwightman/master mrT23 2020-04-12 08:44:42 +0300
• 13cf68850b Remove poorly named metrics from torch imagenet example origins. Use top1/top5 in csv output for consistency with existing validation results files, acc elsewhere. Fixes #111 Ross Wightman 2020-04-10 14:41:08 -0700
• 56608c9070 Bump version for pypi Ross Wightman 2020-04-09 01:46:05 -0700
• 0ebcd2eca1 No default img size for inference script. Fixes #109 Ross Wightman 2020-04-09 01:43:49 -0700
• 1a8f5900ab Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well. Ross Wightman 2020-04-09 01:41:54 -0700
• e01ccb88ce
  Merge pull request #117 from VRandme/typo_eca Ross Wightman 2020-04-07 09:36:31 -0700
• 06a50a94a8 Fix minor typos in create_attn.py and resnet.py #117 Chris Ha 2020-04-07 21:15:57 +0900
• 1a9ab07307 One too many changes at a time, fix missing C #101 Ross Wightman 2020-04-01 13:19:08 -0700
• f17b42bc33 Blur filter no longer a buffer Ross Wightman 2020-04-01 13:15:06 -0700
• 6cdeca24a3 Some cleanup and fixes for initial BlurPool impl. Still some testing and tweaks to go... Ross Wightman 2020-04-01 12:01:59 -0700
• acd1b6cccd Implement Functional Blur on resnet.py Chris Ha 2020-03-22 22:42:55 +0900
• ce3d82b58b Update blurpool.py Chris Ha 2020-03-11 22:19:10 +0900
• 3a287a6e76 Create blurpool.py Chris Ha 2020-03-10 23:27:24 +0900
• c99a5abed4
  Merge pull request #115 from rwightman/mobilenetv2-experiment Ross Wightman 2020-04-05 17:32:06 -0700
• e34074b4da Add final weights for MobileNet-V2 experiments #115 Ross Wightman 2020-04-05 17:31:02 -0700
• a6a5565de7 Fiddling... Ross Wightman 2020-03-19 10:20:20 -0700
• 5a16c533ff Add better resnext50_32x4d weights trained by andravin Ross Wightman 2020-03-18 14:43:50 -0700
• bc998cad91 Experimenting with some MobileNetV2 variations to compare against EfficientNet-Lite Ross Wightman 2020-03-18 13:54:06 -0700
• 71b5cd67da
  Merge pull request #105 from rwightman/efficientnet-lite Ross Wightman 2020-03-18 13:18:27 -0700
• ef30e7f2b6 Update sotabench with EffNet Lite models #105 Ross Wightman 2020-03-18 13:15:54 -0700
• 3406e582cf Add EfficientNet-Lite results, update README Ross Wightman 2020-03-18 13:12:30 -0700
• bd05258f7b EfficientNet-Lite model added w/ converted checkpoints, validation in progress... Ross Wightman 2020-03-17 23:31:45 -0700
• 7deacf5477
  Merge pull request #99 from andravin/save-last Ross Wightman 2020-03-15 11:28:50 -0700
• d92cc4da54 Modified save_checkpoint to always save last checkpoint. Fixes #98. #99 Andrew Lavin 2020-03-09 22:37:39 -0700
• 9419577c90 Experimenting with XSepConv w/ EfficientNet and MobileNetV3... xsepconv Ross Wightman 2020-03-06 20:07:44 -0800
• 8bd08d5f64 Per-stage eca MV3 config, going to shelve these experiments for a while, not proving very productive efficientnet_attn Ross Wightman 2020-03-02 09:46:10 -0800
• f5a5faa104 fix minor typo in resnet.py #95 Chris Ha 2020-03-02 22:39:00 +0900
• 56a78746f2 Revert "Update .gitignore" Chris Ha 2020-03-02 22:33:48 +0900
• aecd7b795d Revert "Create blseresnext-test.ipynb" Chris Ha 2020-03-02 22:32:43 +0900
• 91b13658e0 Create blseresnext-test.ipynb Chris Ha 2020-03-02 20:53:44 +0900
• 3c910705a9 Merge remote-tracking branch 'upstream/master' Chris Ha 2020-03-02 20:53:37 +0900
• 56e2ac3a6d
  Merge pull request #94 from rwightman/lr_noise Ross Wightman 2020-02-29 20:41:05 -0800
• c16f25ced2 Add MobileNetV3 Large weights, results, update README and sotabench for merge #94 Ross Wightman 2020-02-29 20:37:20 -0800
• c60069c1eb Annotate types on drop fns to avoid torchscript error Ross Wightman 2020-02-27 09:30:23 -0800
• ade1ba5fe3 Bring in code that should fix 1d circular padding properly, tweaks to ECA impl, using CECA in MobileNetV3 experiment Ross Wightman 2020-02-25 16:12:41 -0800
• 67e759f710 Adding support to EfficientNet / MobileNetV3 to for different attention layers in .se position Ross Wightman 2020-02-24 18:07:09 -0800
• 9fee316752 Enable fixed fanout calc in EfficientNet/MobileNetV3 weight init by default. Fix #84 Ross Wightman 2020-02-24 15:11:26 -0800
• 27b3680d49 Revamp LR noise, move logic to scheduler base. Fixup PlateauLRScheduler and add it as an option. Ross Wightman 2020-02-22 16:23:15 -0800
• cc5a11abba version bump for PyPi update Ross Wightman 2020-02-22 10:26:19 -0800
• ef80ead3fa Merge remote-tracking branch 'upstream/master' Chris Ha 2020-02-22 17:10:12 +0900
• 514b0938c4 Experimenting with per-epoch learning rate noise w/ step scheduler Ross Wightman 2020-02-21 11:51:05 -0800
• d77f45a6f6 Forgot to add skresnet34 to sotabench Ross Wightman 2020-02-18 15:11:41 -0800
• 6620770665 Simpler approach to loading entrypoints in hubconf works properly Ross Wightman 2020-02-18 14:58:23 -0800
• e0685dd415
  Merge pull request #88 from rwightman/attention Ross Wightman 2020-02-18 14:46:49 -0800
• f1860ef3a5 Update README.md, check in hubconf experiment (fully dynamic) #88 Ross Wightman 2020-02-18 14:41:14 -0800
• 43225d110c Unify drop connect vs drop path under 'drop path' name, switch all EfficientNet/MobilenetV3 refs to 'drop_path'. Update factory to handle new drop args. Ross Wightman 2020-02-18 14:00:26 -0800
• f1d5f8a6c4 Update comments for Selective Kernel and DropBlock/Path impl, add skresnet34 weights Ross Wightman 2020-02-18 13:58:30 -0800
• 670c61b28f Some cutmix/mixup cleanup/fixes Ross Wightman 2020-02-17 11:00:54 -0800
• b3cb5f3275 Working on CutMix impl as per #8, integrating with Mixup, currently experimenting... Ross Wightman 2020-02-16 20:08:17 -0800
• 569419b38d Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch Ross Wightman 2020-02-15 21:18:25 -0800
• 91e2b33d72 Update results with latest NoisyStudent models and SelectiveKernel models Ross Wightman 2020-02-15 20:38:57 -0800
• 53c47479c4 Batch validation batch size adjustment, tweak L2 crop pct Ross Wightman 2020-02-15 20:37:04 -0800
• 9e3987aefd Merge remote-tracking branch 'upstream/master' Chris Ha 2020-02-16 08:49:35 +0900
• 59f4eefb7f Merge branch 'attention' into EcaBam #87 Chris Ha 2020-02-16 08:49:22 +0900
• 08553e16b3 Merge branch 'master' into attention Ross Wightman 2020-02-14 18:24:21 -0800