mirrors
/
pytorch-image-models
mirror of https://github.com/huggingface/pytorch-image-models.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
2,644 Commits
136 Branches
65 Tags
47 MiB
Commit Graph

2644 Commits (faed62171b0bf582329d5589c7613c8d8b481589)
 

Author SHA1 Message Date
Adam J. Stewart faed62171b
timm: add __all__ to __init__ 2025-01-11 14:31:41 +01:00
Ross Wightman 47811bc05a Update README, bump version to 1.0.13 non-dev 2025-01-09 09:33:59 -08:00
Ross Wightman eeee38e972 Avoid unecessary compat break btw train script and nearby timm versions w/ dtype addition. 2025-01-08 21:10:15 -08:00
Ross Wightman deb9895600 Update checkpoint save to fix old hard-link + fuse issue I ran into again... fix #340 2025-01-08 15:36:58 -08:00
Ross Wightman c4fb98f399
Merge pull request #2398 from huggingface/caojiaolong-main 
Merging wandb project name chages w/ addition
 2025-01-08 10:15:09 -08:00
Ross Wightman c173886e75 Merge branch 'main' into caojiaolong-main 2025-01-08 09:11:50 -08:00
Ross Wightman 2d0ac6f567
Merge pull request #2397 from huggingface/half_prec_trainval 
Add half-precision (bfloat16, float16) support to train & validate scripts
 2025-01-07 11:48:02 -08:00
Ross Wightman 1969528296 Fix dtype log when default (None) is used w/o AMP 2025-01-07 11:47:22 -08:00
Ross Wightman 92f610c982 Add half-precision (bfloat16, float16) support to train & validate scripts. Should push dtype handling into model factory / pretrained load at some point... 2025-01-07 10:25:14 -08:00
Jiao-Long Cao 40c19f3939
Add wandb project name argument and allow change wandb run name 2025-01-07 16:43:34 +08:00
Ross Wightman 6f80214e80
Merge pull request #2394 from huggingface/non_reentrant_ckpt 
Wrap torch checkpoint() fn to default use_reentrant flag to False and allow env var override
 2025-01-06 14:44:06 -08:00
Ross Wightman 155f6e7fea Update README, few minor fixups. 2025-01-06 13:09:15 -08:00
Ross Wightman 2b251fb291 Wrap torch checkpoint() fn to default use_reentrant flag to False and allow env var override 2025-01-06 11:28:39 -08:00
Ross Wightman 131518c15c Add comments to MLP layers re expected layouts 2025-01-02 09:41:35 -08:00
Ross Wightman d23facd697
Merge pull request #2388 from laclouis5/fix-mqa-v2 
Fix MQA V2
 2025-01-02 07:48:35 -08:00
Louis Lac 2d5277e858
Merge branch 'main' into fix-mqa-v2 2025-01-02 00:11:22 +01:00
Louis Lac 2d734d9058 Fixed unfused attn2d scale 2025-01-01 12:34:07 -08:00
Louis Lac 6171e756d3 Fix MQA V2 scale and out shape 2025-01-01 15:37:28 +01:00
Ross Wightman 851e0746a9
Update README.md 2024-12-31 14:12:16 -08:00
Ross Wightman e846b2cf28 Add 384x384 in12k pretrain and finetune for convnext_nano 2024-12-31 13:16:43 -08:00
Ross Wightman dafe866047
Update README.md 2024-12-31 10:19:43 -08:00
Ross Wightman 52595a9641
Update README.md 2024-12-31 10:10:52 -08:00
Ruida Zeng 1245b83924 fix: minor typos in UPGRADING 2024-12-31 09:26:13 -08:00
Ruida Zeng 8fd2f48b65 fix: minor typos in README 2024-12-31 09:26:13 -08:00
Ross Wightman b0068ba5d0 Switch hf hub entries for new aimv2 / dfn weights to point to timm locations. Undo forced device for SDR linspace, part of another change. 2024-12-30 19:24:21 -08:00
Ross Wightman cc7fd34015 test filter tweaks 2024-12-30 19:24:21 -08:00
Ross Wightman 1bf84b35c3 Update tests for aimv2 filtering 2024-12-30 19:24:21 -08:00
Ross Wightman b33418713a Add (almost) full set of aimv2 model instances. Switch back to unpacked SwiGLU. Verify correctness. Add DFN L/14 39B weight. 2024-12-30 19:24:21 -08:00
Ross Wightman de35fd87f5 Add SimpleNorm to create_norm factory 2024-12-30 19:24:21 -08:00
Ross Wightman d5375ca769 Use torch F.rms_norm when possible, select fast vs normal paths appropriately and test with torchscript 2024-12-30 19:24:21 -08:00
Ross Wightman 5f12a25114 Add bias arg to Vitamin GeGLU 2024-12-30 19:24:21 -08:00
Ross Wightman 5804d92e4b Switch aimv2 to used packed SwiGLU 2024-12-30 19:24:21 -08:00
Ross Wightman 15406a939e Fixing RmsNorm to fix #2380 and noticed with aimv2 when comparing outputs. Still some work to do, need to look at AMP / fast mode behaviour, dispatch to torch when possible. Add SimpleNorm for 'LayerNorm w/o centering and bias' 2024-12-30 19:24:21 -08:00
Ross Wightman a648a04834 Supporting aimv2 encoders 2024-12-30 19:24:21 -08:00
ariG23498 3a6661ac78 fix broken image link 2024-12-30 07:38:31 -08:00
Ross Wightman 790decc89b Add more pali(2) weights. Switch rest of models adapting open_clip weights to their own weight instances. 2024-12-27 14:00:41 -08:00
Ross Wightman 01cf0f72af Add support for tag, license customization through push_to_hub 2024-12-27 14:00:41 -08:00
Ross Wightman b12ecbd614 Move siglip timm weights to own repos 2024-12-27 14:00:41 -08:00
Ross Wightman 6fb7aaf37d Switching to timm specific weight instances for open_clip image encoders to facilitate hf-hub: use in timm and new transformers TimmWrapper 2024-12-27 14:00:41 -08:00
Ross Wightman 364c567dd2
Merge pull request #2357 from huggingface/more_opt_stuff 
Add caution to Adan. Add decouple decay option to LAMB.
 2024-12-27 12:54:02 -08:00
Ross Wightman a02b1a8e79
Merge pull request #2369 from brianhou0208/fix_reduction 
Fix feature_info.reduction
 2024-12-18 16:51:53 -08:00
Ryan ab0a70dfff fix feature_info.reduction 2024-12-18 21:12:40 +08:00
Ross Wightman ea231079f5
Merge pull request #2361 from huggingface/grodino-dataset_trust_remote 
Dataset trust remote tweaks
 2024-12-06 12:06:56 -08:00
Ross Wightman 7573096eb8 Make sure trust_remote code only passed to HF datasets. Improve some docstrings. 2024-12-06 11:40:04 -08:00
Ross Wightman 95d903fd87 Merge branch 'main' of github.com:grodino/pytorch-image-models into grodino-dataset_trust_remote 2024-12-06 11:14:26 -08:00
Ross Wightman 9eee47de52 Back to dev version 2024-12-06 10:44:41 -08:00
Álvaro Justen (@turicas) 9383f2880d Add cache_dir example 2024-12-06 10:39:13 -08:00
Ross Wightman d1e9a8622a Rename inception_next_atto pretrained str 2024-12-06 10:36:47 -08:00
Weihao Yu 0576175d85 Add inception_next_atto 2024-12-06 10:36:47 -08:00
Ross Wightman 7ab2b938e5 More tweaks to docstrings for hub/builder 2024-12-06 10:25:06 -08:00