Commit Graph

1023 Commits (3cdaf5ed56b508ac11102af36820eea79a6795f0)
 

Author SHA1 Message Date
Ross Wightman 3cdaf5ed56 Add `mmax` config key to auto_augment for increasing upper bound of RandAugment magnitude beyond 10. Make AugMix uniform sampling default not override config setting. 2021-08-12 15:39:05 -07:00
Ross Wightman 1042b8a146 Add non fused LAMB optimizer option 2021-08-09 13:13:43 -07:00
Ross Wightman 01cb46a9a5 Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode. 2021-08-07 16:45:29 -07:00
Ross Wightman bd56946676
Update README.md 2021-07-28 09:00:48 -07:00
Ross Wightman d3f7440650 Add EfficientNetV2 XL model defs 2021-07-22 13:15:24 -07:00
Ross Wightman ef1e2e12be Attempt to fix xcit test failures on github runner by filter largest models 2021-07-13 16:33:55 -07:00
Ross Wightman 72b227dcf5
Merge pull request #750 from drjinying/master
Specify "interpolation" mode in vision_transformer's resize_pos_embed
2021-07-13 11:01:20 -07:00
Ross Wightman 2907c1f967
Merge pull request #746 from samarth4149/master
Adding a Multi Step LR Scheduler
2021-07-13 10:55:54 -07:00
Ross Wightman 5aca7c01e5 Update README.md 2021-07-12 13:33:02 -07:00
Ross Wightman 763329f23f Merge branch 'alexander-soare-xcit' 2021-07-12 13:28:15 -07:00
Ross Wightman 748ab852ca Allow act_layer switch for xcit, fix in_chans for some variants 2021-07-12 13:27:29 -07:00
Ying Jin 20b2d4b69d Use bicubic interpolation in resize_pos_embed() 2021-07-12 10:38:31 -07:00
Ross Wightman d3255adf8e Merge branch 'xcit' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-xcit 2021-07-12 08:30:30 -07:00
Ross Wightman f8039c7492 Fix gc effv2 model cfg name 2021-07-11 12:14:31 -07:00
Alexander Soare 3a55a30ed1 add notes from author 2021-07-11 14:25:58 +01:00
Alexander Soare 899cf84ccc bug fix - missing _dist postfix for many of the 224_dist models 2021-07-11 12:41:51 +01:00
Alexander Soare 623e8b8eb8 wip xcit 2021-07-11 09:39:38 +01:00
Ross Wightman 392368e210 Add efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13 2021-07-09 16:46:52 -07:00
samarth daab57a6d9 1. Added a simple multi step LR scheduler 2021-07-09 16:18:27 -04:00
Ross Wightman 6d8272e92c Add SAM pretrained model defs/weights for ViT B16 and B32 models. 2021-07-08 11:51:12 -07:00
Ross Wightman ee4d8fc69a Remove unecessary line from nest post refactor 2021-07-05 21:22:46 -07:00
Ross Wightman c8ec1ffcb9 Merge branch 'alexander-soare-nested_transformer' 2021-07-05 18:22:50 -07:00
Ross Wightman 8165cacd82 Realized LayerNorm2d won't work in all cases as is, fixed. 2021-07-05 18:21:34 -07:00
Ross Wightman 81cd6863c8 Move aggregation (convpool) for nest into NestLevel, cleanup and enable features_only use. Finalize weight url. 2021-07-05 18:20:49 -07:00
Ross Wightman 6ae0ac6420 Merge branch 'nested_transformer' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-nested_transformer 2021-07-03 12:45:26 -07:00
Alexander Soare 7b8a0017f1 wip to review 2021-07-03 12:10:12 +01:00
Alexander Soare b11d949a06 wip checkpoint with some feature extraction work 2021-07-03 11:45:19 +01:00
Alexander Soare 23bb72ce5e nested_transformer wip 2021-07-02 20:12:29 +01:00
Ross Wightman 7919053425
Merge pull request #729 from bryant1410/patch-3
Add color highlighting to BibTeX entry in README
2021-07-02 10:25:40 -07:00
Santiago Castro 49b38a51e3
Add color highlighting to BibTeX entry in README 2021-06-30 14:07:16 -07:00
Ross Wightman 7096b52a61 Remove sotabench files, no longer working / maintained 2021-06-30 09:25:58 -07:00
Ross Wightman d10b071a28 Update results csvs w/ latest ViT, ResMLP, and NfNet-L2 weights present 2021-06-30 09:11:31 -07:00
Ross Wightman 766b4d3262 Fix features for resnetv2_50t 2021-06-28 15:56:24 -07:00
Ross Wightman e8045e712f Fix BatchNorm for ResNetV2 non GN models, add more ResNetV2 model defs for future experimentation, fix zero_init of last residual for pre-act. 2021-06-28 10:52:45 -07:00
Ross Wightman 02aaa785b9
Update README.md 2021-06-23 14:08:16 -07:00
Ross Wightman 7606bdf9e8
Merge pull request #714 from rwightman/vit_and_bit_test_fixes
Fix a few issues loading pretrained vit/bit npz weights...
2021-06-23 11:36:55 -07:00
Ross Wightman 20a2be14c3 Add gMLP-S weights, 79.6 top-1 2021-06-23 10:40:30 -07:00
Ross Wightman 85f894e03d Fix ViT in21k representation (pre_logits) layer handling across old and new npz checkpoints 2021-06-23 10:38:34 -07:00
Ross Wightman b41cffaa93 Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713 2021-06-22 23:16:05 -07:00
Ross Wightman dc422820ec
Update README.md 2021-06-20 22:12:56 -07:00
Ross Wightman 79927baaec
Merge pull request #702 from rwightman/cleanup_xla_model_fixes
AugReg Vision Transformers, XLA model compat for ResNetV2-BiT / NFNet, ECA-NFNet-L2, GMixer-24 weights, ResMLP official weights, and cleanup
2021-06-20 17:49:14 -07:00
Ross Wightman 9c9755a808 AugReg release 2021-06-20 17:46:06 -07:00
Ross Wightman 381b279785 Add hybrid model fwds back 2021-06-19 22:28:44 -07:00
Ross Wightman 26f04a8e3e Fix a weight link 2021-06-19 16:39:36 -07:00
Ross Wightman 8f4a0222ed Add GMixer-24 MLP model weights, trained w/ TPU + PyTorch XLA 2021-06-18 16:49:28 -07:00
Ross Wightman 4c09a2f169 Bump version 0.4.12 2021-06-18 16:17:34 -07:00
Ross Wightman b319eb5b5d Update ViT weights, more details to be added before merge. 2021-06-18 16:16:49 -07:00
Ross Wightman 8257b86550 Fix up resnetv2 bit/bitm model default res 2021-06-18 16:16:06 -07:00
Ross Wightman 1228f5a3d8 Add BiT distilled 50x1 and teacher 152x2 models from 'A good teacher is patient and consistent' paper. 2021-06-18 11:40:33 -07:00
Ross Wightman 511a8e8c96 Add official ResMLP weights. 2021-06-14 17:03:16 -07:00