4d135421a3
Implement patch dropout for eva / vision_transformer, refactor / improve consistency of dropout args across all vit based models
2023-04-07 20:27:23 -07:00
1bb3989b61
Improve kwarg passthrough for swin, vit, deit, beit, eva
2023-04-05 21:37:16 -07:00
9eaab795c2
Add some vit model deprecations
2023-04-05 17:21:03 -07:00
9aa1133bd2
Fix #1750 , uncomment weight that exists on HF hub, add FIXME to 3 others that are still on local storage
2023-03-31 14:49:30 -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
572f05096a
Swin and FocalNet weights on HF hub. Add model deprecation functionality w/ some registry tweaks.
2023-03-18 14:55:09 -07:00
2e38d53dca
Remove dead line
2023-02-16 16:57:42 -08:00
f77c04ff36
Torchscript fixes/hacks for rms_norm, refactor ParallelScalingBlock with manual combination of input projections, closer paper match
2023-02-16 16:57:42 -08:00
122621daef
Add Final annotation to attn_fas to avoid symbol lookup of new scaled_dot_product_attn fn on old PyTorch in jit
2023-02-16 16:57:42 -08:00
621e1b2182
Add ideas from 'Scaling ViT to 22-B Params', testing PyTorch 2.0 fused F.scaled_dot_product_attention impl in vit, vit_relpos, maxxvit / coatnet.
2023-02-16 16:57:42 -08:00
64667bfa0e
Add 'gigantic' vit clip variant for feature extraction and future fine-tuning
2023-01-25 18:02:10 -08:00
60ebb6cefa
Re-order vit pretrained entries for more sensible default weights (no .tag specified)
2023-01-06 16:12:33 -08:00
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
8ece53e194
Switch BEiT to HF hub weights
2022-12-22 21:43:04 -08:00
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
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
d5e7d6b27e
Merge remote-tracking branch 'origin/main' into refactor-imports
2022-12-09 14:49:44 -08:00
7c4ed4d5a4
Add EVA-large models
2022-12-08 16:21:30 -08:00
927f031293
Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
2022-12-06 15:00:06 -08:00
3785c234d7
Remove clip vit models that won't be ft and comment two that aren't uploaded yet
2022-12-05 10:21:34 -08:00
755570e2d6
Rename _pretrained.py -> pretrained.py, not feasible to change the other files to same scheme without breaking uses
2022-12-05 10:21:34 -08:00
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.
2022-12-05 10:21:34 -08:00
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
2022-12-05 10:21:34 -08:00
b2b6285af7
Add two more FT clip weights
2022-12-05 10:21:34 -08:00
5895056dc4
Add openai b32 ft
2022-12-05 10:21:34 -08:00
9dea5143d5
Adding more clip ft variants
2022-12-05 10:21:34 -08:00
444dcba4ad
CLIP B16 12k weights added
2022-12-05 10:21:34 -08:00
dff4717cbf
Add clip b16 384x384 finetunes
2022-12-05 10:21:34 -08:00
883fa2eeaa
Add fine-tuned B/16 224x224 in1k clip models
2022-12-05 10:21:34 -08:00
9a3d2ac2d5
Add latest CLIP ViT fine-tune pretrained configs / model entrypt updates
2022-12-05 10:21:34 -08:00
def68befa7
Updating vit model defs for mult-weight support trial (vit first). Prepping for CLIP (laion2b and openai) fine-tuned weights.
2022-12-05 10:21:34 -08:00
0dadb4a6e9
Initial multi-weight support, handled so old pretraing config handling co-exists with new tags.
2022-12-05 10:21:34 -08:00
8fda68aff6
Fix repo id bug
...
This to fix this issue #1482
2022-10-05 16:26:06 +02:00
1199c5a1a4
clip_laion2b models need 1e-5 eps for LayerNorm
2022-09-25 10:36:54 -07:00
e069249a2d
Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7
2022-09-16 21:39:05 -07:00
9d65557be3
Fix errant import
2022-09-15 17:47:23 -07:00
9709dbaaa9
Adding support for fine-tune CLIP LAION-2B image tower weights for B/32, L/14, H/14 and g/14. Still WIP
2022-09-15 17:25:59 -07:00
e11efa872d
Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.
2022-09-13 16:35:26 -07:00
0b64117592
Take `no_emb_class` into account when calling `resize_pos_embed`
2022-07-24 19:11:45 +08:00
1b278136c3
Change models with mean 0,0,0 std 1,1,1 from int to float for consistency as mentioned in #1355
2022-07-21 17:36:15 -07:00
a8e34051c1
Unbreak gamma remap impacting beit checkpoint load, version bump to 0.6.4
2022-07-07 23:07:43 -07:00
7d4b3807d5
Support DeiT-3 (Revenge of the ViT) checkpoints. Add non-overlapping (w/ class token) pos-embed support to vit.
2022-07-04 22:25:22 -07:00
7d657d2ef4
Improve resolve_pretrained_cfg behaviour when no cfg exists, warn instead of crash. Improve usability ex #1311
2022-06-24 14:55:25 -07:00
f5ca4141f7
Adjust arg order for recent vit model args, add a few comments
2022-05-02 22:41:38 -07:00
41dc49a337
Vision Transformer refactoring and Rel Pos impl
2022-05-02 15:37:39 -07:00
1618527098
Add layer scale and parallel blocks to vision_transformer
2022-03-23 16:09:07 -07:00
0862e6ebae
Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet
2022-03-19 14:58:54 -07:00
372ad5fa0d
Significant model refactor and additions:
...
* All models updated with revised foward_features / forward_head interface
* Vision transformer and MLP based models consistently output sequence from forward_features (pooling or token selection considered part of 'head')
* WIP param grouping interface to allow consistent grouping of parameters for layer-wise decay across all model types
* Add gradient checkpointing support to a significant % of models, especially popular architectures
* Formatting and interface consistency improvements across models
* layer-wise LR decay impl part of optimizer factory w/ scale support in scheduler
* Poolformer and Volo architectures added
2022-02-28 13:56:23 -08:00
5f81d4de23
Move DeiT to own file, vit getting crowded. Working towards fixing #1029 , make pooling interface for transformers and mlp closer to convnets. Still working through some details...
2022-01-26 22:53:57 -08:00
95cfc9b3e8
Merge remote-tracking branch 'origin/master' into norm_norm_norm
2022-01-25 22:20:45 -08:00
Ross Wightman
Mohamed Rashad
Ceshine Lee