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

• 88b7912e78
  Update requirements.txt Sangdoo Yun 2020-07-25 12:37:30 +0900
• ff7e5842d8
  Update optim_factory.py Sangdoo Yun 2020-07-25 12:36:28 +0900
• 64857fee65
  Update optim_factory.py Sangdoo Yun 2020-07-25 12:35:46 +0900
• 7271e81cbb
  Create sgdp.py Sangdoo Yun 2020-07-25 12:32:03 +0900
• 3bf15b91ed
  Update __init__.py Sangdoo Yun 2020-07-25 12:31:39 +0900
• 65ff050712
  Create adamp.py Sangdoo Yun 2020-07-25 12:31:28 +0900
• f096a438c0
  Update __init__.py Sangdoo Yun 2020-07-25 12:30:34 +0900
• 08016e839d Cleanup FeatureInfo getters, add TF models sourced Xception41/65/71 weights Ross Wightman 2020-07-24 17:59:21 -0700
• 7ba5a384d3 Add ReXNet w/ remapped weights, feature support Ross Wightman 2020-07-23 10:28:57 -0700
• 4fae5f4c0e
  Update optim_factory.py Sangdoo Yun 2020-07-22 11:04:01 +0900
• 629b35cbcb
  Update requirements.txt Sangdoo Yun 2020-07-22 11:02:32 +0900
• b24fb86fea
  Update __init__.py Sangdoo Yun 2020-07-22 11:02:05 +0900
• c9d54bc1c3 Add HRNet feature extraction, fix senet type, lower feature testing res to 96x96 Ross Wightman 2020-07-21 17:39:29 -0700
• 2ac663f340 Add feature support to legacy senets, add 32x32 resnext models to exclude list for feature testing. Ross Wightman 2020-07-21 11:15:30 -0700
• 701dba303e Again Ross Wightman 2020-07-21 08:53:51 -0700
• 648ba41b4b Try again with the worfklow threads Ross Wightman 2020-07-21 08:52:56 -0700
• 52b6e72e86 Try defining num threads for github workflow tests explicity (2) Ross Wightman 2020-07-21 08:49:11 -0700
• c146b54abc Cleanup EfficientNet/MobileNetV3 feature extraction a bit, only two tap locations now, small mobilenetv3 models work Ross Wightman 2020-07-21 01:21:38 -0700
• 68fd8a267b Merge branch 'master' into features Ross Wightman 2020-07-20 16:11:38 -0700
• 4e61c6a12d Cleanup, refactoring of Feature extraction code, add tests, fix tests, non hook feature extraction working with torchscript Ross Wightman 2020-07-20 16:10:31 -0700
• 6eec3fb4a4 Move FeatureHooks into features.py, switch EfficientNet, MobileNetV3 to use build model helper Ross Wightman 2020-07-19 15:00:43 -0700
• 9eba134d79 More models supporting feature extraction, xception, gluon_xception, inception_v3, inception_v4, pnasnet, nasnet, dla. Fix DLA unused projection params. Ross Wightman 2020-07-19 14:02:02 -0700
• 298fba09ac Back out some activation hacks trialing upcoming pytorch changes Ross Wightman 2020-07-17 18:41:37 -0700
• 3b9004bef9 Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces Ross Wightman 2020-07-17 17:54:26 -0700
• f4ac7563bf
  Update download URL for HTTP 403 Error #191 Chanran Kim 2020-07-17 13:56:09 +0900
• e2cc481310 Update CSP ResNets for cross expansion without activation. Fix VovNet IABN compatibility with fixed activation arg. Ross Wightman 2020-07-13 16:24:55 -0700
• 3b6cce4c95 Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs. Ross Wightman 2020-07-13 14:59:39 -0700
• c402bd28b5
  Merge pull request #1 from jhyau/first_commit Jacqueline Yau 2020-07-12 20:59:12 -0700
• 01608cd912 Edited readme to include the steps followed when first running the ResNeXt50 model Jacqueline Yau 2020-07-12 20:58:13 -0700
• 3aebc2f06c Switch DPN to use BnAct layer, train a new DPN 68b model with RA to 79.21 Ross Wightman 2020-07-12 11:13:06 -0700
• 17f4dd2778 Merge branch 'michalwols-docs' v0.1-rexnet Ross Wightman 2020-07-10 12:39:20 -0700
• 3a63858dd8 Deployed 022130d with MkDocs version: 1.1.2 Ross Wightman 2020-07-10 11:37:04 -0800
• 022130d229 Merge branch 'docs' of https://github.com/michalwols/pytorch-image-models into michalwols-docs Ross Wightman 2020-07-10 12:05:59 -0700
• 31cf1251c1
  Update setup.py Ross Wightman 2020-07-09 09:42:36 -0700
• 0d5550c1e2
  Merge pull request #183 from KushajveerSingh/results_diff Ross Wightman 2020-07-09 09:41:38 -0700
• 5699e8429f set precision=2 in param_count #183 KushajveerSingh 2020-07-09 16:43:11 +0530
• 6526ccb4a7 set precision=3 in results KushajveerSingh 2020-07-09 16:38:49 +0530
• 856f6181f7 add {rank,top1,top5}_diff in results KushajveerSingh 2020-07-09 03:48:26 +0530
• f122f0274b Significant ResNet refactor: * stage creation + make_layer moved to separate fn with more sensible dilation/output_stride calc * drop path rate decay easy to impl with refactored block creation loops * fix dilation + blur pool combo Ross Wightman 2020-07-05 00:48:12 -0700
• 2608918e8d configure mkdocs based documentation #179 michal 2020-07-03 19:54:17 -0400
• a66df5fb91 More model feature extraction support, start to deprecate senet.py, dilations added to regnet, add proper aligned xception Ross Wightman 2020-07-03 00:41:30 -0700
• 7729f40dca Fix another bug, update all gluon resnet models to use new creation method (feature support) Ross Wightman 2020-06-30 16:44:15 -0700
• d72ac0db25 Fix #173, lr cycle default 0 vs 1. Fix #177, mirror resnest weights for future stability. Ross Wightman 2020-06-29 21:31:48 -0700
• d0113f9cdb Fix a few issues that came up in tests Ross Wightman 2020-06-29 21:13:21 -0700
• d23a2697d0 Working on feature extraction, interfaces refined, a number of models working, some in progress. Ross Wightman 2020-06-29 17:45:38 -0700
• 24e7535278 Remove tests from distrib v0.1-resnest Ross Wightman 2020-06-16 22:57:26 -0700
• 328339a086 Add ESE-VoVNet-19-DW weights Ross Wightman 2020-06-15 14:31:55 -0700
• 2d83752bc2 Fix default interpolation/crop of largest 2 ResNeSt models Ross Wightman 2020-06-12 16:42:47 -0700
• f225ae8e59 Update README with model results and attribution. Make scheduler factory bit more robust to arg differences, add noise to plateau lr and fix min/max. Ross Wightman 2020-06-12 13:33:12 -0700
• d1b5dddad1
  Merge pull request #155 from rwightman/densenet_update_and_more Ross Wightman 2020-06-11 17:01:19 -0700
• 39f27c1add Almost ready to merge, vovnet typo, version bump, readme addition #155 Ross Wightman 2020-06-11 15:41:58 -0700
• 151679c2f1 Add custom grad tests, fix cut & paste error with hard_mish ME, add a few more pytorch act fns to factory Ross Wightman 2020-06-11 14:49:23 -0700
• 6c7932fe75 Update sotabench.py, tweak VovNet cfg Ross Wightman 2020-06-11 14:34:25 -0700
• d3ee3de96a Update validation script first batch prime and clear cuda cache between multi-model runs Ross Wightman 2020-06-11 13:34:21 -0700
• 0aca08384f Update regnet cfg keys to match model names so registry works properly Ross Wightman 2020-06-09 14:37:45 -0700
• b41b8d0108 Update results csv files Ross Wightman 2020-06-09 14:36:24 -0700
• 78fa0772cc Leverage python hierachical logger #163 Antoine Broyelle 2020-06-09 18:28:48 +0100
• 13c0a6290e Add ESE-VovNet39 weights, 79.32 top-1 Ross Wightman 2020-06-06 22:49:19 -0700
• 4ddde1d3a4 Fix two regressions Ross Wightman 2020-06-05 11:04:51 -0700
• a7e8cadd15 Remove pointless densenet configs, add an iabn version of 264 as it makes more sense to try someday... Ross Wightman 2020-06-03 17:13:52 -0700
• e78daf586a better densenet121 and densenetblur121d weights Ross Wightman 2020-06-03 13:30:03 -0700
• 7be299504f Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size) Ross Wightman 2020-06-03 00:00:37 -0700
• 88129b2569 Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit. Ross Wightman 2020-06-02 21:06:10 -0700
• f28170df3f Fix an an untested change, remove a debug print Ross Wightman 2020-06-01 17:26:42 -0700
• eb7653614f Monster commit, activation refactor, VoVNet, norm_act improvements, more * refactor activations into basic PyTorch, jit scripted, and memory efficient custom auto * implement hard-mish, better grad for hard-swish * add initial VovNet V1/V2 impl, fix #151 * VovNet and DenseNet first models to use NormAct layers (support BatchNormAct2d, EvoNorm, InplaceIABN) * Wrap IABN for any models that use it * make more models torchscript compatible (DPN, PNasNet, Res2Net, SelecSLS) and add tests Ross Wightman 2020-06-01 16:59:51 -0700
• ff94ffce61 Merge branch 'master' into densenet_update_and_more Ross Wightman 2020-05-26 00:02:57 -0700
• 62fea452a3
  Update activations.py #156 bonlime 2020-05-25 12:15:36 +0300
• 5966654052 Update requirements so PyTorch 1.4 is min, add separate sotabench reqs to force 1.4 and prevent error with 1.5 Ross Wightman 2020-05-24 13:28:03 -0700
• 0ea53cecc3 Merge branch 'master' into densenet_update_and_more Ross Wightman 2020-05-22 16:18:10 -0700
• 6441e9cc1b Fix memory_efficient mode for DenseNets. Add AntiAliasing (Blur) support for DenseNets and create one test model. Add lr cycle/mul params to train args. Ross Wightman 2020-05-22 16:16:45 -0700
• d79ac48626 Update sotabench.py Ross Wightman 2020-05-22 14:42:43 -0700
• e881383b4e
  Merge pull request #154 from rwightman/tests_bugfixes Ross Wightman 2020-05-21 19:44:12 -0700
• 4d13db538f Add x48d ResNext101s to test exclude for ubuntu #154 Ross Wightman 2020-05-21 19:13:41 -0700
• 4212cd3b9f Another attempt at getting Ubuntu test runner to work Ross Wightman 2020-05-21 18:55:10 -0700
• 20329f2630 Bring down test resolutions to see if we can at least do a fwd on the L2 models Ross Wightman 2020-05-21 16:49:46 -0700
• 3873ea710e Minor test change Ross Wightman 2020-05-21 15:51:47 -0700
• afb6bd0669 Add backward and default_cfg tests and fix a few issues found. Fix #153 Ross Wightman 2020-05-21 15:28:36 -0700
• ea2e59ca36
  Merge pull request #150 from rwightman/regnet Ross Wightman 2020-05-18 00:26:40 -0700
• 50658b9a67 Add RegNet models and weights #150 Ross Wightman 2020-05-18 00:08:52 -0700
• 6454efa71e Merge branch 'master' of https://github.com/rwightman/pytorch-image-models into fix_reset_classifier #142 Vyacheslav Shults 2020-05-15 11:38:31 +0300
• 7df83258c9 Merge branch 'master' into densenet_update_and_more Ross Wightman 2020-05-13 23:34:44 -0700
• dab9935b36
  Merge pull request #148 from rwightman/drop_block_improve v0.1-regnet Ross Wightman 2020-05-13 16:30:34 -0700
• 1904ed8fec Improve dropblock impl, add fast variant, and better AMP speed, inplace, batchwise... few ResNeSt cleanups #148 Ross Wightman 2020-05-13 15:17:08 -0700
• 63addb741f
  Merge pull request #146 from rwightman/inceptionv3_fix Ross Wightman 2020-05-12 22:03:37 -0700
• 17270c69b9 Remove annoying InceptionV3 dependency on scipy and insanely slow trunc_norm init. Bring InceptionV3 code into this codebase and use upcoming torch trunch_norm_ init. #146 Ross Wightman 2020-05-12 21:59:34 -0700
• c4ca016656
  Merge pull request #145 from rwightman/resnest Ross Wightman 2020-05-12 13:38:29 -0700
• 208e7912f7 Missed one of the abalation model entrypoints, update README #145 Ross Wightman 2020-05-12 13:36:31 -0700
• 5bd1ad13e7 Refactor test indent Ross Wightman 2020-05-12 13:07:46 -0700
• 9cc289f18c Exclude EfficientNet-L2 models from test Ross Wightman 2020-05-12 13:07:03 -0700
• 2f884a0ce5 Add resnest14, resnest26, and two of the abalation grouped resnest50 models Ross Wightman 2020-05-12 12:21:52 -0700
• f4cdc2ac31 Add ResNeSt models Ross Wightman 2020-05-11 23:27:09 -0700
• 780860d140 Add norm_act factory method, move JIT of norm layers to factory Ross Wightman 2020-05-09 22:07:01 -0700
• 14edacdf9a DenseNet converted to support ABN (norm + act) modules. Experimenting with EvoNorm, IABN Ross Wightman 2020-05-09 18:26:41 -0700
• e545bb9401
  Update test_inference.py Ross Wightman 2020-05-07 10:15:49 -0700
• 305a2db705
  Update test_inference.py Ross Wightman 2020-05-07 10:14:24 -0700
• 022ed001f3 Update DenseNet to latest in Torchvision (torchscript compat, checkpointing, proper init). Start adding ehanced configurability, stem options... Ross Wightman 2020-05-07 09:57:48 -0700
• 14e01b878c
  Merge pull request #143 from michalwols/master Ross Wightman 2020-05-07 09:47:13 -0700
• 8c77f14cae Install cpu version of torch on ubuntu #143 michal 2020-05-07 01:09:16 -0400
• 69d725c9fe Basic forward pass test for all registered models michal 2020-05-07 00:20:58 -0400
• 8da43e0617 Install extra dependencies required by some models and log test durations michal 2020-05-07 00:20:34 -0400