Commit Graph

1141 Commits (0b1f84142f2274ee305c94b1d8c9125966be2a8a)

Author SHA1 Message Date
Fredo Guan 1d882eb494 Update metaformers.py
2 years ago
Fredo Guan 2209d0830e Update metaformers.py
2 years ago
Fredo Guan 32bede4e27 Update metaformers.py
2 years ago
Fredo Guan 4ed934e000 Update metaformers.py
2 years ago
Fredo Guan 3f0b075367 Update metaformers.py
2 years ago
Fredo Guan cf28c57fda Update metaformers.py
2 years ago
Fredo Guan 2fef9006d7 Update metaformers.py
2 years ago
Fredo Guan 6b6510f30a Update metaformers.py
2 years ago
Fredo Guan 808f4a7ebd Update metaformers.py
2 years ago
Fredo Guan bee9576f03 Update metaformers.py
2 years ago
Fredo Guan 9bf9d163bc Update metaformers.py
2 years ago
Fredo Guan 13876ada4c Update metaformers.py
2 years ago
Fredo Guan 473403d905 Update metaformers.py
2 years ago
Fredo Guan 09d1ea628d Update metaformers.py
2 years ago
Fredo Guan bfa6f0962d Update metaformers.py
2 years ago
Fredo Guan 5fe33b33a0 Merge branch 'metaformer_baselines_for_vision' of https://github.com/fffffgggg54/pytorch-image-models into metaformer_baselines_for_vision
2 years ago
Fredo Guan 5de2544a80 Update metaformers.py
2 years ago
Fredo Guan eaf54b66af Update metaformers.py
2 years ago
Fredo Guan 55d4eb78a2 merge with poolformer, initial version
2 years ago
Fredo Guan 81ca323751
Davit update formatting and fix grad checkpointing (#7)
2 years ago
Ross Wightman e9aac412de Correct mean/std for CLIP convnexts
2 years ago
Ross Wightman 42bd8f7bcb Add convnext_base CLIP image tower weights for fine-tuning / features
2 years ago
Ross Wightman e520553e3e Update batchnorm freezing to handle NormAct variants, Add GroupNorm1Act, update BatchNormAct2d tracing change from PyTorch
2 years ago
Fredo Guan 5f2bebd7ca Update metaformers.py
2 years ago
Fredo Guan 2a9f93c064 Update metaformers.py
2 years ago
Fredo Guan 087a451337 Update metaformers.py
2 years ago
Fredo Guan 1b1b1d83b4 Update metaformers.py
2 years ago
Fredo Guan f400e8a3c9 Update metaformers.py
2 years ago
Fredo Guan d40d4c8c2a Update metaformers.py
2 years ago
Fredo Guan 7869dd6769 Update metaformers.py
2 years ago
Fredo Guan a73e464bc8 Update metaformers.py
2 years ago
Fredo Guan 0a9c2607a0 Update metaformers.py
2 years ago
Fredo Guan 199b443884 Update metaformers.py
2 years ago
Fredo Guan 61e8414ad0 Update metaformers.py
2 years ago
Fredo Guan 95ec7cf016 Update metaformers.py
2 years ago
Fredo Guan a776d98d3f Update metaformers.py
2 years ago
Ross Wightman a2c14c2064 Add tiny/small in12k pretrained and fine-tuned ConvNeXt models
2 years ago
Ross Wightman 01aea8c1bf Version 0.8.6dev0
2 years ago
Ross Wightman 2e83bba142 Revert head norm changes to ConvNeXt as it broke some downstream use, alternate workaround for fcmae weights
2 years ago
Ross Wightman 1825b5e314 maxxvit type
2 years ago
Ross Wightman 5078b28f8a More kwarg handling tweaks, maxvit_base_rw def added
2 years ago
Ross Wightman c0d7388a1b Improving kwarg merging in more models
2 years ago
Fredo Guan 8dbba278b7 Update metaformers.py
2 years ago
Fredo Guan 3e3010b65e Update metaformers.py
2 years ago
Fredo Guan cc8575e9d1 Update metaformers.py
2 years ago
Fredo Guan bde9554604 Update metaformers.py
2 years ago
Fredo Guan 464ae0fe50 Update metaformers.py
2 years ago
Fredo Guan 8568bc7b6a Update metaformers.py
2 years ago
Fredo Guan ddfdb543dc Update metaformers.py
2 years ago
Fredo Guan 4e682f1fda Update metaformers.py
2 years ago
Fredo Guan bc37dec29b Update metaformers.py
2 years ago
Fredo Guan 0aa784027e Update metaformers.py
2 years ago
Fredo Guan 1145720bec Update metaformers.py
2 years ago
Fredo Guan 4cfecf8acb Update metaformers.py
2 years ago
Fredo Guan 1b3318bf19 Update metaformers.py
2 years ago
Fredo Guan 944fd549c4 Update metaformers.py
2 years ago
Fredo Guan 7aa3459caf Update metaformers.py
2 years ago
Fredo Guan 7f149f31d4 Update metaformers.py
2 years ago
Fredo Guan 926d886527 Update metaformers.py
2 years ago
Fredo Guan 358c4ae7ec Update metaformers.py
2 years ago
Fredo Guan f71beadc29 Update metaformers.py
2 years ago
Fredo Guan fcaf9b8d23 Update metaformers.py
2 years ago
Fredo Guan d484d86189 Update metaformers.py
2 years ago
Fredo Guan d90ed530dc Update metaformers.py
2 years ago
Fredo Guan ec202b4d16 Update metaformers.py
2 years ago
Fredo Guan 0bde1c1218 Update metaformers.py
2 years ago
Fredo Guan 42741b7cdb Update metaformers.py
2 years ago
Fredo Guan 116345b4d3 Update metaformers.py
2 years ago
Fredo Guan ee16588a3a Update metaformers.py
2 years ago
Fredo Guan c7e1819ca5 Update metaformers.py
2 years ago
Fredo Guan 01f671ed08 Update metaformers.py
2 years ago
Fredo Guan d17bcb10a5 Update metaformers.py
2 years ago
Fredo Guan 1f3a661160 Update metaformers.py
2 years ago
Fredo Guan 530709d299 update
2 years ago
Ross Wightman ae9153052f
Update version.py
2 years ago
Ross Wightman 60ebb6cefa Re-order vit pretrained entries for more sensible default weights (no .tag specified)
2 years ago
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.
2 years ago
Ross Wightman add3fb864e Working on improved model card template for push_to_hf_hub
2 years ago
Ross Wightman dd0bb327e9
Update version.py
2 years ago
Ross Wightman 6e5553da5f
Add ConvNeXt-V2 support (model additions and weights) (#1614)
2 years ago
Ross Wightman 6902c48a5f Fix ResNet based models to work w/ norm layers w/o affine params. Reformat long arg lists into vertical form.
2 years ago
Ross Wightman d5aa17e415 Remove print from auto_augment
2 years ago
Ross Wightman 7c846d9970 Better vmap compat across recent torch versions
2 years ago
Ross Wightman 4e24f75289
Merge pull request #1593 from rwightman/multi-weight_effnet_convnext
2 years ago
Ross Wightman 8ece53e194 Switch BEiT to HF hub weights
2 years ago
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.
2 years ago
Ross Wightman e2fc43bc63 Version 0.8.2dev0
2 years ago
Ross Wightman 9a51e4ea2e Add FlexiViT models and weights, refactoring, push more weights
2 years ago
Fredo Guan 10b3f696b4
Davit std (#6)
2 years ago
Ross Wightman 656e1776de Convert mobilenetv3 to multi-weight, tweak PretrainedCfg metadata
2 years ago
Fredo Guan 546590c5f5
Merge branch 'rwightman:main' into main
2 years ago
Ross Wightman 6a01101905 Update efficientnet.py and convnext.py to multi-weight, add ImageNet-12k pretrained EfficientNet-B5 and ConvNeXt-Nano.
2 years ago
alec.tu 74d6afb4cd Add Adan to __init__.py
2 years ago
Fredo Guan 84178fca60
Merge branch 'rwightman:main' into main
2 years ago
Fredo Guan c43340ddd4
Davit std (#5)
2 years ago
Ross Wightman e7da205345 Fix aa min_max level clamp
2 years ago
Ross Wightman e3b2f5be0a Add 3-Augment support to auto_augment.py, clean up weighted choice handling, and allow adjust per op prob via arg string
2 years ago
Ross Wightman d5e7d6b27e Merge remote-tracking branch 'origin/main' into refactor-imports
2 years ago
Ross Wightman cda39b35bd Add a deprecation phase to module re-org
2 years ago
Fredo Guan edea013dd1
Davit std (#3)
2 years ago