Commit Graph

1022 Commits (bed350f5e584241a753d22b94ab36146ad824c2e)

Author SHA1 Message Date
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.
2 years ago
Ross Wightman ca38e1e73f Update ClassifierHead module, add reset() method, update in_chs -> in_features for consistency
2 years ago
Ross Wightman 8ab573cd26 Add convnext_tiny and convnext_small 384x384 fine-tunes of in12k weights, fix pool size for laion CLIP convnext weights
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
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
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
Ross Wightman 656e1776de Convert mobilenetv3 to multi-weight, tweak PretrainedCfg metadata
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
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
Ross Wightman 7c4ed4d5a4 Add EVA-large models
2 years ago
Ross Wightman 98047ef5e3 Add EVA FT results, hopefully fix BEiT test failures
2 years ago
Ross Wightman 3cc4d7a894 Fix missing register for 224 eva model
2 years ago
Ross Wightman eba07b0de7 Add eva models to beit.py
2 years ago
Ross Wightman 927f031293 Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
2 years ago
Ross Wightman 3785c234d7 Remove clip vit models that won't be ft and comment two that aren't uploaded yet
2 years ago
Ross Wightman f82239b30e multi-weight branch version -> 0.8.0dev
2 years ago
Ross Wightman 755570e2d6 Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses
2 years ago
Ross Wightman 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.
2 years ago
Ross Wightman 4d5c395160 MaxVit, ViT, ConvNeXt, and EfficientNet-v2 updates
2 years ago
Ross Wightman 3db4e346e0 Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default
2 years ago
Ross Wightman 9da7e3a799 Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
2 years ago
Ross Wightman b2b6285af7 Add two more FT clip weights
2 years ago
Ross Wightman 5895056dc4 Add openai b32 ft
2 years ago
Ross Wightman 9dea5143d5 Adding more clip ft variants
2 years ago
Ross Wightman 444dcba4ad CLIP B16 12k weights added
2 years ago
Ross Wightman dff4717cbf Add clip b16 384x384 finetunes
2 years ago