Ross Wightman
ea9c9550b2
Fully move ViT hybrids to their own file, including embedding module. Remove some extra DeiT models that were for benchmarking only.
2021-04-01 14:17:38 -07:00
Ross Wightman
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
2021-04-01 12:15:34 -07:00
Ross Wightman
7953e5d11a
Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433
2021-03-31 23:11:28 -07:00
Ross Wightman
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
2021-03-31 18:21:02 -07:00
Ross Wightman
cf5fec5047
Cleanup experimental vit weight init a bit
2021-03-20 09:44:24 -07:00
Ross Wightman
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
2021-03-18 23:15:48 -07:00
Ross Wightman
4de57ccf01
Add weight init scheme that's closer to JAX impl
2021-03-18 15:35:22 -07:00
Ross Wightman
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
2021-03-17 13:18:52 -07:00
Ross Wightman
d584e7f617
Support for huggingface hub via create_model and default_cfgs.
...
* improve consistency of model creation helper fns
* add comments to some of the model helpers
* support passing external default_cfgs so they can be sourced from hub
2021-03-16 22:48:26 -07:00
Ross Wightman
17cdee7354
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
2021-03-01 16:53:32 -08:00
Ross Wightman
0706d05d52
Benchmark models listed in txt file. Add more hybrid vit variants for testing
2021-02-28 16:00:33 -08:00
Ross Wightman
de97be9146
Spell out diff between my small and deit small vit models.
2021-02-23 16:22:55 -08:00
Ross Wightman
f0ffdf89b3
Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.
2021-02-23 15:54:55 -08:00
Ross Wightman
5a8e1e643e
Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.
2021-01-27 22:06:57 -08:00
Ross Wightman
bb50ac4708
Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args.
2021-01-25 11:05:23 -08:00
Ross Wightman
c16e965037
Add some ViT comments and fix a few minor issues.
2021-01-24 23:18:35 -08:00
Ross Wightman
55f7dfa9ea
Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing
2021-01-18 16:11:02 -08:00
Ross Wightman
855d6cc217
More dataset work including factories and a tensorflow datasets (TFDS) wrapper
...
* Add parser/dataset factory methods for more flexible dataset & parser creation
* Add dataset parser that wraps TFDS image classification datasets
* Tweak num_classes handling bug for 21k models
* Add initial deit models so they can be benchmarked in next csv results runs
2021-01-15 17:26:20 -08:00
Ross Wightman
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
2020-12-28 16:59:15 -08:00
Ross Wightman
231d04e91a
ResNetV2 pre-act and non-preact model, w/ BiT pretrained weights and support for ViT R50 model. Tweaks for in21k num_classes passing. More to do... tests failing.
2020-12-28 16:59:15 -08:00
Ross Wightman
b401952caf
Add newly added vision transformer large/base 224x224 weights ported from JAX official repo
2020-10-29 17:31:01 -07:00
Ross Wightman
61200db0ab
in_chans=1 working w/ pretrained weights for vision_transformer
2020-10-29 15:49:36 -07:00
Ross Wightman
f591e90b0d
Make sure num_features attr is present in vit models as with others
2020-10-29 15:33:47 -07:00
Ross Wightman
f944242cb0
Fix #262 , num_classes arg mixup. Make vision_transformers a bit closer to other models wrt get/reset classfier/forward_features. Fix torchscript for ViT.
2020-10-29 13:58:28 -07:00
Ross Wightman
736f209e7d
Update vision transformers to be compatible with official code. Port official ViT weights from jax impl.
2020-10-26 18:42:11 -07:00
Ross Wightman
27a93e9de7
Improve test crop for ViT models. Small now 77.85, added base weights at 79.35 top-1.
2020-10-21 23:35:25 -07:00
Ross Wightman
d4db9e7977
Add small vision transformer weights. 77.42 top-1.
2020-10-21 12:14:12 -07:00
Ross Wightman
f31933cb37
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
2020-10-13 13:33:44 -07:00
