Ross Wightman
e9f1376cde
Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn
2023-01-20 14:47:55 -08:00
Ross Wightman
bed350f5e5
Push all MaxxViT weights to HF hub, cleanup impl, add feature map extraction support and prompote to 'std' architecture. Fix norm head for proper embedding / feat map output. Add new in12k + ft 1k weights.
2023-01-20 14:45:25 -08:00
Ross Wightman
ca38e1e73f
Update ClassifierHead module, add reset() method, update in_chs -> in_features for consistency
2023-01-20 14:44:05 -08:00
Ross Wightman
8ab573cd26
Add convnext_tiny and convnext_small 384x384 fine-tunes of in12k weights, fix pool size for laion CLIP convnext weights
2023-01-20 14:40:16 -08:00
Fredo Guan
e58a884c1c
Merge remote-tracking branch 'upstream/main'
2023-01-15 14:37:52 -08:00
Fredo Guan
81ca323751
Davit update formatting and fix grad checkpointing ( #7 )
...
fixed head to gap->norm->fc as per convnext, along with option for norm->gap->fc
failed tests due to clip convnext models, davit tests passed
2023-01-15 14:34:56 -08:00
Ross Wightman
e9aac412de
Correct mean/std for CLIP convnexts
2023-01-14 22:53:56 -08:00
Ross Wightman
42bd8f7bcb
Add convnext_base CLIP image tower weights for fine-tuning / features
2023-01-14 21:16:29 -08:00
Ross Wightman
65aea97067
Update tests.yml
...
Attempt to work around flaky azure ubuntu mirrors
2023-01-12 21:31:44 -08:00
Ross Wightman
dd60c45044
Merge pull request #1633 from rwightman/freeze_norm_revisit
...
Update batchnorm freezing to handle NormAct variants
2023-01-12 21:13:58 -08:00
Ross Wightman
e520553e3e
Update batchnorm freezing to handle NormAct variants, Add GroupNorm1Act, update BatchNormAct2d tracing change from PyTorch
2023-01-12 16:55:47 -08:00
Ross Wightman
a2c14c2064
Add tiny/small in12k pretrained and fine-tuned ConvNeXt models
2023-01-11 14:50:39 -08:00
Ross Wightman
c061d5e401
Allow using class_map functionality w/ IterableDataset (TFDS/WDS) to remap class labels
2023-01-09 16:28:47 -08:00
Ross Wightman
01fdf44438
Initial focalnet import, more refactoring needed for timm.
2023-01-09 16:18:19 -08:00
Ross Wightman
01aea8c1bf
Version 0.8.6dev0
2023-01-09 13:38:31 -08:00
Ross Wightman
2e83bba142
Revert head norm changes to ConvNeXt as it broke some downstream use, alternate workaround for fcmae weights
2023-01-09 13:37:40 -08:00
Ikko Eltociear Ashimine
2c24cb98f1
Fix typo in results/README.md
...
occuring -> occurring
2023-01-09 12:23:39 -08:00
Ross Wightman
1825b5e314
maxxvit type
2023-01-09 08:57:31 -08:00
Ross Wightman
5078b28f8a
More kwarg handling tweaks, maxvit_base_rw def added
2023-01-09 08:57:31 -08:00
Ross Wightman
c0d7388a1b
Improving kwarg merging in more models
2023-01-09 08:57:31 -08:00
Ross Wightman
94a91598c3
Update README.md
2023-01-06 21:39:25 -08:00
Ross Wightman
d2ef5a3a94
Update README.md
2023-01-06 21:38:40 -08:00
Ross Wightman
ae9153052f
Update version.py
2023-01-06 17:17:35 -08:00
Ross Wightman
60ebb6cefa
Re-order vit pretrained entries for more sensible default weights (no .tag specified)
2023-01-06 16:12:33 -08:00
Ross Wightman
e861b74cf8
Pass through --model-kwargs (and --opt-kwargs for train) from command line through to model __init__. Update some models to improve arg overlay. Cleanup along the way.
2023-01-06 16:12:33 -08:00
Ross Wightman
add3fb864e
Working on improved model card template for push_to_hf_hub
2023-01-06 16:12:33 -08:00
Xa9aX ツ
13c7183c52
Update installation.mdx
2023-01-06 09:16:43 -08:00
Ross Wightman
eb83eb3bd1
Rotate changelogs, add redirects to mkdocs -> equivalent HF docs pages
2023-01-05 17:27:13 -08:00
Ross Wightman
dd0bb327e9
Update version.py
...
Ver 0.8.4dev0
2023-01-05 07:55:18 -08:00
Ross Wightman
6e5553da5f
Add ConvNeXt-V2 support (model additions and weights) ( #1614 )
...
* Add ConvNeXt-V2 support (model additions and weights)
* ConvNeXt-V2 weights on HF Hub, tweaking some tests
* Update README, fixing convnextv2 tests
2023-01-05 07:53:32 -08:00
nateraw
3698e79ac5
🐛 fix github source links in hf docs
2023-01-04 09:42:05 -08:00
Nathan Raw
9f5bba9ef9
Structure Hugging Face Docs ( #1575 )
...
* 🎨 structure docs
* 🚧 wip docs
* 📝 add installation doc
* 📝 wip docs
* 📝 wip docs
* 📝 wip docs
* 📝 wip docs
* 📝 wip docs
* 📝 add basic reference docs
* 📝 remove augmentation from toctree
* 👷 update pr doc builder to bugfix branch
* 📝 wip docs
* 🚧 wip
* 👷 bump CI
* 🚧 wip
* 🚧 bump CI
* 🚧 wip
* 🚧 wip
* 🚧 wip
* 📝 add hf hub tutorial doc
* 🔥 remove inference tut
* 🚧 wip
* 📝 wip docs
* 📝 wip docs
* 📝 update docs
* 📝 move validation script doc up in order
* 🎨 restructure to remove legacy docs
* 📝 update index doc
* 📝 update number of pretrained models
* Update hfdocs/README.md
* Update .github/workflows/build_pr_documentation.yml
* Update build_pr_documentation.yml
* bump
* 📌 update gh action to use main branch
* 🔥 remove comment
2023-01-03 14:13:53 -08:00
Ross Wightman
960f5f92e6
Update results csv with latest val/test set runs
2022-12-30 15:42:41 -08:00
Ross Wightman
6902c48a5f
Fix ResNet based models to work w/ norm layers w/o affine params. Reformat long arg lists into vertical form.
2022-12-29 16:32:26 -08:00
Ross Wightman
d5aa17e415
Remove print from auto_augment
2022-12-28 17:11:35 -08:00
Ross Wightman
7c846d9970
Better vmap compat across recent torch versions
2022-12-24 14:37:04 -08:00
Ross Wightman
130458988a
Update README.md
2022-12-23 15:20:43 -08:00
Ross Wightman
d96538f1d2
Update README
2022-12-23 15:19:54 -08:00
Ross Wightman
4e24f75289
Merge pull request #1593 from rwightman/multi-weight_effnet_convnext
...
Update efficientnet.py and convnext.py to multi-weight, add new 12k pretrained weights
2022-12-23 10:09:08 -08:00
Ross Wightman
8ece53e194
Switch BEiT to HF hub weights
2022-12-22 21:43:04 -08:00
Ross Wightman
d1bfa9a000
Support HF datasets and TFSD w/ a sub-path by fixing split, fix #1598 ... add class mapping support to HF datasets in case class label isn't in info.
2022-12-22 21:34:13 -08:00
Ross Wightman
35fb00c779
Add flexivit to non-std tests list
2022-12-22 21:32:31 -08:00
Ross Wightman
e2fc43bc63
Version 0.8.2dev0
2022-12-22 17:34:09 -08:00
Ross Wightman
9a51e4ea2e
Add FlexiViT models and weights, refactoring, push more weights
...
* push all vision_transformer*.py weights to HF hub
* finalize more pretrained tags for pushed weights
* refactor pos_embed files and module locations, move some pos embed modules to layers
* tweak hf hub helpers to aid bulk uploading and updating
2022-12-22 17:23:09 -08:00
Fredo Guan
10b3f696b4
Davit std ( #6 )
...
Separate patch_embed module
2022-12-16 21:50:28 -08:00
Ross Wightman
656e1776de
Convert mobilenetv3 to multi-weight, tweak PretrainedCfg metadata
2022-12-16 09:29:13 -08:00
Fredo Guan
546590c5f5
Merge branch 'rwightman:main' into main
2022-12-14 23:44:15 -08:00
Ross Wightman
18ec173f95
Merge pull request #1592 from twmht/add_adan_to_init
...
Add Adan to __init__.py
2022-12-14 20:43:12 -08:00
Ross Wightman
6a01101905
Update efficientnet.py and convnext.py to multi-weight, add ImageNet-12k pretrained EfficientNet-B5 and ConvNeXt-Nano.
2022-12-14 20:33:23 -08:00
alec.tu
74d6afb4cd
Add Adan to __init__.py
2022-12-15 11:37:29 +08:00
