067c7281e2
Another test filter adjustment
2023-03-31 08:33:26 -07:00
3825812f1a
Update test filtering for enormoous
2023-03-31 00:04:56 -07:00
0737bd3ec8
eva02 non-CLIP weights on HF hub, add initial eva02 clip model configs w/ postnorm variant & attn LN
2023-03-30 23:43:59 -07:00
ac67098147
Add final attr for fast_attn on beit / eva
2023-03-28 08:40:40 -07:00
1885bdc431
Merge pull request #1745 from huggingface/mw-mlp_mixer
...
MLP-Mixer multi-weight support, HF hub push
2023-03-28 07:55:17 -07:00
2362f79062
Merge pull request #1748 from huggingface/mw-deit
...
Multi-weight and HF hub for deit / deit3
2023-03-28 07:54:58 -07:00
a84abe6656
Add eva02 to non-std test models
2023-03-27 22:56:52 -07:00
e9f427b953
Add hf hub entries for mlp_mixer
2023-03-27 22:50:43 -07:00
cff81deb78
multi-weight and hf hub for deit / deit3
2023-03-27 22:47:16 -07:00
3863d63516
Adding EVA02 weights and model defs, move beit based eva_giant to same eva.py file. Cleanup rotary pos, add lang oriented freq bands to be compat with eva design choice. Fix #1738
2023-03-27 17:16:07 -07:00
b12060996c
MLP-Mixer multi-weight support, hf hub push
2023-03-27 16:42:13 -07:00
56b90317cd
Change torchrun args to use _ instead of -, - is the new format, but looks like _ still works for backward compat with old versions. Fix #1742
2023-03-26 20:23:55 -07:00
d196fa536d
Fix last min torchscript regression in nfnet changes
2023-03-24 00:10:17 -07:00
33ada0cbca
Add group_matcher to focalnet for proper layer-wise LR decay
2023-03-23 23:21:49 -07:00
b271dc0e16
NFNet multi-weight support + HF hub push
2023-03-23 23:20:38 -07:00
a089bfba2d
Version 0.8.17dev0
2023-03-22 15:40:23 -07:00
9e327c9932
Update README
2023-03-22 15:40:10 -07:00
dbd33e4b62
Update crop settings for new rexnet weights
2023-03-22 15:39:49 -07:00
da6bdd4560
Update resnetv2.py for multi-weight and HF hub weights
2023-03-22 15:38:04 -07:00
b3e816d6d7
Improve filtering behaviour for tag + non-tagged model wildcard consistency.
2023-03-22 10:21:22 -07:00
7aba64ebdb
Add update byobnet.py w/ models pushed to HF hub
2023-03-22 10:00:00 -07:00
e7ef8335bf
regnet.py multi-weight conversion, new ImageNet-12k pretrain/ft from timm for y_120 and y_160, also new tv v2, swag, & seer weights for push to Hf hub.
2023-03-21 15:51:49 -07:00
c78319adce
Add ImageNet-12k ReXNet-R 200 & 300 weights, and push existing ReXNet models to HF hub. Dilation support added to rexnet
2023-03-20 13:48:17 -07:00
8db20dc240
Fix #1726 , dropout not used in NormMlpClassifierHead. Make dropout more consistent across both classifier heads (nn.Dropout)
2023-03-20 09:37:05 -07:00
041de79f9e
Fix numel use in helpers for checkpoint remap
2023-03-20 09:36:48 -07:00
2054f11c6f
Switch to torchrun as old launcher changed arg names in 2.0.. Fix #1728
2023-03-20 08:15:40 -07:00
49b9c3be80
Include pretrained tag in deprecated mapping warning
2023-03-19 21:21:19 -07:00
0d5c5c39fc
Merge pull request #1628 from huggingface/focalnet_and_swin_refactor
...
Add FocalNet arch, refactor Swin V1/V2 for better feature extraction and HF hub multi-weight support
2023-03-18 20:09:36 -07:00
fafac3317c
Version 0.8.16dev0
2023-03-18 15:09:20 -07:00
3448cc689c
Use gather (fancy indexing) for valid labels instead of bool mask in validate.py
2023-03-18 15:08:19 -07:00
9fcfb8bcc1
Add Microsoft FocalNet specific ('ms') ImageNet-22k classifier layout
2023-03-18 14:57:34 -07:00
572f05096a
Swin and FocalNet weights on HF hub. Add model deprecation functionality w/ some registry tweaks.
2023-03-18 14:55:09 -07:00
2fc5ac3d18
Exclude the large models from default_cfgs, failing github CI
2023-03-16 14:51:20 -07:00
5aebad3fbc
return_map back to out_map for _feature helpers
2023-03-16 14:50:55 -07:00
acfd85ad68
All swin models support spatial output, add output_fmt to v1/v2 and use ClassifierHead.
...
* update ClassifierHead to allow different input format
* add output format support to patch embed
* fix some flatten issues for a few conv head models
* add Format enum and helpers for tensor format (layout) choices
2023-03-15 23:21:51 -07:00
c30a160d3e
Merge remote-tracking branch 'origin/main' into focalnet_and_swin_refactor
2023-03-15 15:58:39 -07:00
cd3ee78387
Merge pull request #1715 from huggingface/convnext_shortcut
...
Add support to ConvNextBlock for downsample and ch expansion. Fix #1699
2023-03-13 15:27:03 -07:00
ad94d737b7
Add support to ConvNextBlock for downsample and channel expansion to improve stand alone use. Fix #1699
2023-03-13 14:06:24 -07:00
aa8c0708df
Merge pull request #1714 from SWHL/main
...
Fix typo
2023-03-11 13:29:14 -10:00
43e6143bef
Fix #1712 broken support for AMP w/ PyTorch < 1.10. Disable loss scaler for bfloat16
2023-03-11 15:26:09 -08:00
3a636eee71
Fix #1713 missed assignement in 3-aug level fn, fix few other minor lint complaints in auto_augment.py
2023-03-11 14:32:23 -08:00
82cb47bcf3
Merge pull request #1708 from pkluska/chore/mvitv2-coreml-exportable
...
chore: Modify the MobileVitV2Block to be coreml exportable
2023-03-11 11:52:20 -10:00
7c6523edd0
Fix typo
2023-03-09 10:42:54 +08:00
992bf7c3d4
chore: Modify the MobileVitV2Block to be coreml exportable
...
based on is_exportable() set variable controlling behaviour of the block
CoreMLTools support im2col from 6.2 version, unfortunately col2im
is still not supported.
Tested with exporting to ONNX, Torchscript, CoreML, and TVM.
2023-03-03 09:38:24 +01:00
4b8cfa6c0a
Add convnext_xxlarge CLIP image tower weights, version 0.8.15dev0
2023-02-26 21:51:48 -08:00
80a0bb216c
Merge pull request #1696 from huggingface/convnext_xxlarge_eps
...
Add default norm_eps=1e-5 for convnext_xxlarge, improve kwarg merging for all convnext models
2023-02-26 13:39:20 -08:00
f9b56a1bfa
Version 0.8.14dev0
2023-02-26 13:38:51 -08:00
1c13ef7b46
Add default norm_eps=1e-5 for convnext_xxlarge, improve kwarg merging for all convnext models
2023-02-26 12:11:49 -08:00
450b74affb
Update README.md
...
Remove references to github.io docs that died with repo move
2023-02-24 14:43:31 -08:00
10627bbd49
CI: Split CI tests to run them in parallel ( #1691 )
...
* Split CI tests to run them in parallel
The idea of this PR is to split tests into multiple sets that can be run
in parallel by GH. For this, all tests in test_models.py that would run
on GH get a pytest marker. The GH workflow matrix is factorized to run
only a single marker. That way, only a subset of tests should run per
worker, leading to quicker results.
There is also a worker that runs all the tests that are not inside
test_models.py.
* [skip ci] empty commit to abort ci
* Fix typo in marker name
* Split fx into forward and backward
* Comment out test coverage for now
Checking if it's responsible for regression in CI runtime.
* Remove pytest cov completely from requirements
* Remove cov call in pyproject.toml
Missed that one.
2023-02-24 12:28:57 -08:00
Ross Wightman
Ross Wightman
SWHL
Piotr Sebastian Kluska
Benjamin Bossan