372ad5fa0d
Significant model refactor and additions:
...
* All models updated with revised foward_features / forward_head interface
* Vision transformer and MLP based models consistently output sequence from forward_features (pooling or token selection considered part of 'head')
* WIP param grouping interface to allow consistent grouping of parameters for layer-wise decay across all model types
* Add gradient checkpointing support to a significant % of models, especially popular architectures
* Formatting and interface consistency improvements across models
* layer-wise LR decay impl part of optimizer factory w/ scale support in scheduler
* Poolformer and Volo architectures added
2022-02-28 13:56:23 -08:00
5f81d4de23
Move DeiT to own file, vit getting crowded. Working towards fixing #1029 , make pooling interface for transformers and mlp closer to convnets. Still working through some details...
2022-01-26 22:53:57 -08:00
95cfc9b3e8
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2022-01-25 22:20:45 -08:00
abc9ba2544
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
2022-01-25 21:54:13 -08:00
010b486590
Add Dino pretrained weights (no head) for vit models. Add support to tests and helpers for models w/ no classifier (num_classes=0 in pretrained cfg)
2022-01-17 12:20:02 -08:00
a8d103e18b
Giant/gigantic vits snuck through in a test a broke GitHub test runner, add filter
2022-01-14 17:23:35 -08:00
ef72ad4177
Extra vit_huge model likely to cause test issue (non in21k variant), adding to filters
2022-01-14 16:28:27 -08:00
e967c72875
Update REAMDE.md. Sneak in g/G (giant / gigantic?) ViT defs from scaling paper
2022-01-14 16:28:27 -08:00
4df51f3932
Add lcnet_100 and mnasnet_small weights
2022-01-06 22:21:05 -08:00
5ccf682a8f
Remove deprecated bn-tf train arg and create_model handler. Add evos/evob models back into fx test filter until norm_norm_norm branch merged.
2022-01-06 18:08:39 -08:00
25d1526092
Update pytest for GitHub runner to use --forked with xdist, hopefully eliminate memory buildup
2022-01-06 16:04:23 -08:00
cd059cbe9c
Add FX backward tests back
2021-12-01 14:58:56 -08:00
58ffa2bfb7
Update pytest for GitHub runner to use --forked with xdist, hopefully eliminate memory buildup
2021-12-01 12:09:23 -08:00
f7d210d759
Remove evonorm models from FX tests
2021-11-24 13:21:24 -08:00
f83b0b01e3
Would like to pass GitHub tests again disabling both FX feature extract backward and torchscript tests
2021-11-23 22:24:58 -08:00
147e1059a8
Remove FX backward test from GitHub actions runs for now.
2021-11-23 14:32:32 -08:00
878bee1d5e
Add patch8 vit model to FX exclusion filter
2021-11-22 14:00:27 -08:00
ce76a810c2
New FX test strategy, filter based on param count
2021-11-22 11:48:40 -08:00
1e51c2d02e
More FX test tweaks
2021-11-22 09:46:43 -08:00
90448031ea
Filter more large models from FX tests
2021-11-21 21:26:44 -08:00
8dc269c303
Filter more models for FX tests
2021-11-21 19:49:33 -08:00
2482652027
Add nfnet_f2 to FX test exclusion
2021-11-21 14:08:53 -08:00
05092e2fbe
Add more models to FX filter
2021-11-20 15:51:48 -08:00
3819bef93e
Add FX test exclusion since it uses more ram and barfs on GitHub actions. Will take a few iterations to include needed models :(
2021-11-19 17:35:41 -08:00
9b3519545d
Attempt to reduce memory footprint of FX tests for GitHub actions runs
2021-11-19 14:24:12 -08:00
bdd3dff0ca
beit_large models killing GitHub actions test, filter out
2021-11-19 08:39:48 -08:00
f2006b2437
Cleanup qkv_bias cat in beit model so it can be traced
2021-11-18 21:25:00 -08:00
1076a65df1
Minor post FX merge cleanup
2021-11-18 19:47:07 -08:00
0262a0e8e1
fx ready for review
2021-11-13 00:06:33 +00:00
d2994016e9
Add try/except guards
2021-11-12 21:16:53 +00:00
b25ff96768
wip - pre-rebase
2021-11-12 20:45:05 +00:00
a6c24b936b
Tests to enforce all models FX traceable
2021-11-12 20:45:05 +00:00
6d2acec1bb
Fix ordering of tests
2021-10-02 16:10:11 +01:00
65c3d78b96
Freeze unfreeze functionality finalized. Tests added
2021-10-02 15:55:08 +01:00
24720abe3b
Merge branch 'master' into attn_update
2021-09-13 16:51:10 -07:00
1c9284c640
Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now
2021-09-13 16:38:23 -07:00
7ab2491ab7
Better handling of crossvit for tests / forward_features, fix torchscript regression in my changes
2021-09-13 13:01:05 -07:00
f1808e0970
Post crossvit merge cleanup, change model names to reflect input size, cleanup img size vs scale handling, fix tests
2021-09-13 11:49:54 -07:00
a897e0ebcc
Merge branch 'feature/crossvit' of https://github.com/chunfuchen/pytorch-image-models into chunfuchen-feature/crossvit
2021-09-10 17:38:37 -07:00
8642401e88
Swap botnet 26/50 weights/models after realizing a mistake in arch def, now figuring out why they were so low...
2021-09-05 15:17:19 -07:00
5f12de4875
Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.
2021-09-05 12:41:14 -07:00
54e90e82a5
Another attempt at sgd momentum test passing...
2021-09-03 20:50:26 -07:00
7ab9d4555c
add crossvit
2021-09-01 17:13:12 -04:00
fc894c375c
Another attempt at sgd momentum test passing...
2021-08-27 10:39:31 -07:00
708d87a813
Fix ViT SAM weight compat as weights at URL changed to not use repr layer. Fix #825 . Tweak optim test.
2021-08-27 09:20:13 -07:00
c207e02782
MOAR optimizer changes. Woo!
2021-08-18 22:20:35 -07:00
42c1f0cf6c
Fix lars tests
2021-08-18 21:05:34 -07:00
a426511c95
More optimizer cleanup. Change all to no longer use .data. Improve (b)float16 use with adabelief. Add XLA compatible Lars.
2021-08-18 17:21:56 -07:00
a6af48be64
add madgradw optimizer
2021-08-17 22:19:27 -07:00
55fb5eedf6
Remove experiment from lamb impl
2021-08-17 21:48:26 -07:00
Ross Wightman
Alexander Soare
Richard Chen