Commit Graph

1818 Commits (965d0a2d363668b7f8d1794e45c52d525bdb6278)
 

Author SHA1 Message Date
Ross Wightman 965d0a2d36 fast_attn -> fused_attn, implement global config for enable/disable fused_attn, add to more models. vit clip openai 336 weights. 2023-04-10 12:04:33 -07:00
Ross Wightman 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
Ross Wightman 1bb3989b61 Improve kwarg passthrough for swin, vit, deit, beit, eva 2023-04-05 21:37:16 -07:00
Ross Wightman a09e240cd6
Merge pull request #1756 from huggingface/mw-resnet
ResNet models on HF hub, multi-weight support
2023-04-05 17:42:48 -07:00
Ross Wightman 35c94b836c Update warning message for deprecated model names 2023-04-05 17:24:17 -07:00
Ross Wightman 9eaab795c2 Add some vit model deprecations 2023-04-05 17:21:03 -07:00
Ross Wightman b17abd35b2 Version 0.8.19dev0 2023-04-05 16:37:16 -07:00
Ross Wightman 647ba98d23 Update README 2023-04-05 16:37:07 -07:00
Ross Wightman abff3f12ec Wrong pool_size for 288 ft 2023-04-05 16:07:51 -07:00
Ross Wightman 356309959c ResNet models on HF hub, multi-weight support, add torchvision v2 weights, new 12k pretrained and fine-tuned timm anti-aliased weights 2023-04-05 14:19:42 -07:00
Ross Wightman 7501972cd6 Version 0.8.18dev0 2023-03-31 16:51:26 -07:00
Ross Wightman a84bf11887 Update README 2023-03-31 16:51:02 -07:00
Ross Wightman beef7f0a22 Add ImageNet-12k intermediate fine-tunes of convnext base & large CLIP models, add first 1k fine-tune of xxlarge 2023-03-31 16:45:01 -07:00
Ross Wightman 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
Ross Wightman 3e45db4853
Update README.md 2023-03-31 12:24:10 -07:00
Ross Wightman 7326470514
Merge pull request #1746 from huggingface/eva02
Adding EVA02 weights and model defs
2023-03-31 12:17:00 -07:00
Ross Wightman adeb9de7c6 Mismatch in eva pretrained_cfg vs model for one of the clip variants 2023-03-31 10:30:30 -07:00
Ross Wightman 85f6cb6637 Update README 2023-03-31 08:42:51 -07:00
Ross Wightman 067c7281e2 Another test filter adjustment 2023-03-31 08:33:26 -07:00
Ross Wightman 3825812f1a Update test filtering for enormoous 2023-03-31 00:04:56 -07:00
Ross Wightman 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
Ross Wightman ac67098147 Add final attr for fast_attn on beit / eva 2023-03-28 08:40:40 -07:00
Ross Wightman 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
Ross Wightman 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
Ross Wightman a84abe6656 Add eva02 to non-std test models 2023-03-27 22:56:52 -07:00
Ross Wightman e9f427b953 Add hf hub entries for mlp_mixer 2023-03-27 22:50:43 -07:00
Ross Wightman cff81deb78 multi-weight and hf hub for deit / deit3 2023-03-27 22:47:16 -07:00
Ross Wightman 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
Ross Wightman b12060996c MLP-Mixer multi-weight support, hf hub push 2023-03-27 16:42:13 -07:00
Ross Wightman 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
Ross Wightman d196fa536d Fix last min torchscript regression in nfnet changes 2023-03-24 00:10:17 -07:00
Ross Wightman 33ada0cbca Add group_matcher to focalnet for proper layer-wise LR decay 2023-03-23 23:21:49 -07:00
Ross Wightman b271dc0e16 NFNet multi-weight support + HF hub push 2023-03-23 23:20:38 -07:00
Ross Wightman a089bfba2d Version 0.8.17dev0 2023-03-22 15:40:23 -07:00
Ross Wightman 9e327c9932 Update README 2023-03-22 15:40:10 -07:00
Ross Wightman dbd33e4b62 Update crop settings for new rexnet weights 2023-03-22 15:39:49 -07:00
Ross Wightman da6bdd4560 Update resnetv2.py for multi-weight and HF hub weights 2023-03-22 15:38:04 -07:00
Ross Wightman b3e816d6d7 Improve filtering behaviour for tag + non-tagged model wildcard consistency. 2023-03-22 10:21:22 -07:00
Ross Wightman 7aba64ebdb Add update byobnet.py w/ models pushed to HF hub 2023-03-22 10:00:00 -07:00
Ross Wightman 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
Ross Wightman 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
Ross Wightman 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
Ross Wightman 041de79f9e Fix numel use in helpers for checkpoint remap 2023-03-20 09:36:48 -07:00
Ross Wightman 2054f11c6f Switch to torchrun as old launcher changed arg names in 2.0.. Fix #1728 2023-03-20 08:15:40 -07:00
Ross Wightman 49b9c3be80 Include pretrained tag in deprecated mapping warning 2023-03-19 21:21:19 -07:00
Ross Wightman 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
Ross Wightman fafac3317c Version 0.8.16dev0 2023-03-18 15:09:20 -07:00
Ross Wightman 3448cc689c Use gather (fancy indexing) for valid labels instead of bool mask in validate.py 2023-03-18 15:08:19 -07:00
Ross Wightman 9fcfb8bcc1 Add Microsoft FocalNet specific ('ms') ImageNet-22k classifier layout 2023-03-18 14:57:34 -07:00
Ross Wightman 572f05096a Swin and FocalNet weights on HF hub. Add model deprecation functionality w/ some registry tweaks. 2023-03-18 14:55:09 -07:00