8568bc7b6a
Update metaformers.py
3 years ago
ddfdb543dc
Update metaformers.py
3 years ago
4e682f1fda
Update metaformers.py
3 years ago
bc37dec29b
Update metaformers.py
3 years ago
0aa784027e
Update metaformers.py
3 years ago
1145720bec
Update metaformers.py
3 years ago
4cfecf8acb
Update metaformers.py
3 years ago
1b3318bf19
Update metaformers.py
3 years ago
944fd549c4
Update metaformers.py
3 years ago
7aa3459caf
Update metaformers.py
3 years ago
7f149f31d4
Update metaformers.py
3 years ago
926d886527
Update metaformers.py
3 years ago
358c4ae7ec
Update metaformers.py
3 years ago
f71beadc29
Update metaformers.py
3 years ago
fcaf9b8d23
Update metaformers.py
3 years ago
d484d86189
Update metaformers.py
3 years ago
d90ed530dc
Update metaformers.py
3 years ago
ec202b4d16
Update metaformers.py
3 years ago
0bde1c1218
Update metaformers.py
3 years ago
42741b7cdb
Update metaformers.py
3 years ago
116345b4d3
Update metaformers.py
3 years ago
ee16588a3a
Update metaformers.py
3 years ago
c7e1819ca5
Update metaformers.py
3 years ago
01f671ed08
Update metaformers.py
3 years ago
d17bcb10a5
Update metaformers.py
3 years ago
1f3a661160
Update metaformers.py
3 years ago
530709d299
update
3 years ago
60ebb6cefa
Re-order vit pretrained entries for more sensible default weights (no .tag specified)
3 years ago
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.
3 years ago
add3fb864e
Working on improved model card template for push_to_hf_hub
3 years ago
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
3 years ago
6902c48a5f
Fix ResNet based models to work w/ norm layers w/o affine params. Reformat long arg lists into vertical form.
3 years ago
8ece53e194
Switch BEiT to HF hub weights
3 years ago
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
3 years ago
656e1776de
Convert mobilenetv3 to multi-weight, tweak PretrainedCfg metadata
3 years ago
6a01101905
Update efficientnet.py and convnext.py to multi-weight, add ImageNet-12k pretrained EfficientNet-B5 and ConvNeXt-Nano.
3 years ago
d5e7d6b27e
Merge remote-tracking branch 'origin/main' into refactor-imports
3 years ago
cda39b35bd
Add a deprecation phase to module re-org
3 years ago
7c4ed4d5a4
Add EVA-large models
3 years ago
98047ef5e3
Add EVA FT results, hopefully fix BEiT test failures
3 years ago
3cc4d7a894
Fix missing register for 224 eva model
3 years ago
eba07b0de7
Add eva models to beit.py
3 years ago
927f031293
Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
3 years ago
3785c234d7
Remove clip vit models that won't be ft and comment two that aren't uploaded yet
3 years ago
755570e2d6
Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses
3 years ago
72cfa57761
Add ported Tensorflow MaxVit weights. Add a few more CLIP ViT fine-tunes. Tweak some model tag names. Improve model tag name sorting. Update HF hub push config layout.
3 years ago
4d5c395160
MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates
...
* Add support for TF weights and modelling specifics to MaxVit (testing ported weights)
* More fine-tuned CLIP ViT configs
* ConvNeXt and MaxVit updated to new pretrained cfgs use
* EfficientNetV2, MaxVit and ConvNeXt high res models use squash crop/resize
3 years ago
9da7e3a799
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
3 years ago
b2b6285af7
Add two more FT clip weights
3 years ago
5895056dc4
Add openai b32 ft
3 years ago
Fredo Guan