pytorch-image-models

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

0a853990e7 Add distributed sampler that maintains order of original dataset (for validation) Ross Wightman 2019-04-22 17:34:24 -0700
8fbd62a169 Exclude batchnorm and bias params from weight_decay by default Ross Wightman 2019-04-22 17:33:22 -0700
34cd76899f Add Single-Path NAS pixel1 model Ross Wightman 2019-04-22 12:43:45 -0700
419555be62 Update a few GenMobileNet comments Ross Wightman 2019-04-21 16:14:23 -0700
1cf3ea0467

Update README.md Ross Wightman 2019-04-21 16:49:00 -0700
bc264269c9 Morph mnasnet impl into a generic mobilenet that covers Mnasnet, MobileNetV1/V2, ChamNet, FBNet, and related * add an alternate RMSprop opt that applies eps like TF * add bn params for passing through alternates and changing defaults to TF style Ross Wightman 2019-04-21 15:54:28 -0700
e9c7961efc Fix pooling in mnasnet, more sensible default for AMP opt level Ross Wightman 2019-04-17 18:06:37 -0700
996c77aa94 Prep mnasnet for pretrained models, use the select global pool, some comment mistakes Ross Wightman 2019-04-15 16:58:40 -0700
6b4f9ba223 Add MNASNet A1, B1, and Small models as per the TF impl. Testing/training in progress... Ross Wightman 2019-04-15 09:02:55 -0700
c88e80081d Fix missing cfg key check Ross Wightman 2019-04-15 08:45:31 -0700
073d31a076

Update README.md Ross Wightman 2019-04-14 15:19:58 -0700
7ba78aaaeb

Update README.md Ross Wightman 2019-04-14 15:14:37 -0700
e8e8bce335

Create README.md Ross Wightman 2019-04-14 15:10:52 -0700
9e296dbffb Add seresnet26_32x4d cfg and weights + interpolation str->PIL enum fn Ross Wightman 2019-04-14 13:43:46 -0700
71afec86d3 Loader tweaks Ross Wightman 2019-04-13 14:52:38 -0700
79f615639e Add pretrained weights for seresnet18 Ross Wightman 2019-04-13 14:52:21 -0700
8a33a6c90a Add checkpoint clean script, add link to pretrained resnext50 weights Ross Wightman 2019-04-13 14:15:35 -0700
6e9697eb9c Fix small bug in seresnet input size and eval transform handling of img size Ross Wightman 2019-04-13 10:06:43 -0700
db1fe34d0c Update a few comment, add some references Ross Wightman 2019-04-12 23:16:49 -0700
0562b91c38 Add per model crop pct, interpolation defaults, tie it all together * create one resolve fn to pull together model defaults + cmd line args * update attribution comments in some models * test update train/validation/inference scripts Ross Wightman 2019-04-12 22:49:35 -0700
c328b155e9 Random erasing crash fix and args pass through Ross Wightman 2019-04-11 22:06:43 -0700
9c3859fb9c Uniform pretrained model handling. * All models have 'default_cfgs' dict * load/resume/pretrained helpers factored out * pretrained load operates on state_dict based on default_cfg * test all models in validate * schedule, optim factor factored out * test time pool wrapper applied based on default_cfg Ross Wightman 2019-04-11 21:32:16 -0700
63e677d03b Merge branch 'master' of github.com:rwightman/pytorch-models Ross Wightman 2019-04-10 14:55:54 -0700
0bc50e84f8 Lots of refactoring and cleanup. * Move 'test time pool' to Module that can be used by any model, remove from DPN * Remove ResNext model file and combine with ResNet * Remove fbresnet200 as it was an old conversion and pretrained performance not worth param count * Cleanup adaptive avgmax pooling and add back conctat variant * Factor out checkpoint load fn Ross Wightman 2019-04-10 14:12:28 -0700
f1cd1a5ce3 Cleanup CheckpointSaver, add support for increasing or decreasing metric, switch to prec1 metric in train loop Ross Wightman 2019-04-07 10:22:55 -0700
c0e6e5f3db Add common model interface to pnasnet and xception, update factory Ross Wightman 2019-04-06 13:59:15 -0700
f2029dfb65 Add smooth loss Ross Wightman 2019-04-05 20:50:26 -0700
b0158a593e Fix distributed train script Ross Wightman 2019-04-05 20:49:58 -0700
183d8e4aef Xception model working Ross Wightman 2019-04-05 12:09:25 -0700
1e23727f2f Update inference script for new loader style Ross Wightman 2019-04-05 11:58:16 -0700
58571e992e Change block avgpool in senets to mean for performance issues with NVIDIA and AMP especially Ross Wightman 2019-04-05 10:53:13 -0700
5180f94c7e Distributed (multi-process) train, multi-gpu single process train, and NVIDIA AMP support Ross Wightman 2019-04-05 10:51:39 -0700
6f9a0c8ef2 Merge branch 'master' of github.com:rwightman/pytorch-models Ross Wightman 2019-04-01 11:07:05 -0700
5cb1a35c6b Fixup Resnext, remove alternate shortcut types Ross Wightman 2019-04-01 11:03:37 -0700
d87824bd65 Merge branch 'master' of github.com:rwightman/pytorch-models Ross Wightman 2019-03-17 09:57:36 -0700
45cde6f0c7 Improve creation of data pipeline with prefetch enabled vs disabled, fixup inception_res_v2 and dpn models Ross Wightman 2019-03-11 22:17:42 -0700
321435e6b4 Update resnext init Ross Wightman 2019-03-10 14:24:39 -0700
2295cf56c2 Add some Nvidia performance enhancements (prefetch loader, fast collate), and refactor some of training and model fact/transforms Ross Wightman 2019-03-10 14:23:16 -0700
9d927a389a Add adabound, random erasing Ross Wightman 2019-03-01 22:03:42 -0800
1577c52976 Resnext added, changes to bring it and seresnet in line with rest of models Ross Wightman 2019-03-01 15:29:02 -0800
e0cfeb7d8e Add some models, remove a model, tweak some models Ross Wightman 2019-03-01 13:08:35 -0800
31055466fc Fixup validate/inference script args, fix senet init for better test accuracy Ross Wightman 2019-02-22 14:07:50 -0800
b1a5a71151 Update schedulers Ross Wightman 2019-02-17 12:50:15 -0800
b5255960d9 Tweaking tanh scheduler, senet weight init (for BN), transform defaults Ross Wightman 2019-02-13 23:11:09 -0800
48360625f2 Cycle limit on tanh sched Ross Wightman 2019-02-08 21:47:27 -0800
824f42e75e Forgot to include Tanh scheduler Ross Wightman 2019-02-08 21:14:47 -0800
a336e5bff3 Minor updates Ross Wightman 2019-02-08 20:56:24 -0800
cf0c280e1b Cleanup tranforms, add custom schedulers, tweak senet34 model Ross Wightman 2019-02-06 20:19:11 -0800
c57717d325 Fix tta train bug, improve logging Ross Wightman 2019-02-02 10:17:04 -0800
72b4d162a2 Increase training performance Ross Wightman 2019-02-01 22:48:31 -0800
5855b07ae0 Initial commit, puting some ol pieces together Ross Wightman 2019-02-01 21:48:56 -0800