b049a5c5c6
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2022-03-21 13:41:43 -07:00
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
1420c118df
Missed comitting outstanding changes to default_cfg keys and test exclusions for swin v2
2022-02-23 19:50:26 -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
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
7ab9d4555c
add crossvit
2021-09-01 17:13:12 -04:00
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
ef1e2e12be
Attempt to fix xcit test failures on github runner by filter largest models
2021-07-13 16:33:55 -07:00
623e8b8eb8
wip xcit
2021-07-11 09:39:38 +01:00
7b8a0017f1
wip to review
2021-07-03 12:10:12 +01:00
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
381b279785
Add hybrid model fwds back
2021-06-19 22:28:44 -07:00
0020268d9b
Try lower max size for non_std default_cfg test
2021-06-12 23:31:24 -07:00
8880f696b6
Refactoring, cleanup, improved test coverage.
...
* Add eca_nfnet_l2 weights, 84.7 @ 384x384
* All 'non-std' (ie transformer / mlp) models have classifier / default_cfg test added
* Fix #694 reset_classifer / num_features / forward_features / num_classes=0 consistency for transformer / mlp models
* Add direct loading of npz to vision transformer (pure transformer so far, hybrid to come)
* Rename vit_deit* to deit_*
* Remove some deprecated vit hybrid model defs
* Clean up classifier flatten for conv classifiers and unusual cases (mobilenetv3/ghostnet)
* Remove explicit model fns for levit conv, just pass in arg
2021-06-12 16:40:02 -07:00
17dc47c8e6
Missed comma in test filters.
2021-05-30 22:00:43 -07:00
8bf63b6c6c
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
2021-05-30 12:47:02 -07:00
9c78de8c02
Fix #661 , move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
2021-05-26 15:28:42 -07:00
5db7452173
Fix visformer in_chans stem handling
2021-05-25 14:11:36 -07:00
Ross Wightman
Alexander Soare
Richard Chen