mirrors/pytorch-image-models
1
0
Fork 0
mirror of https://github.com/huggingface/pytorch-image-models.git synced 2025-06-03 15:01:08 +08:00
Code Issues Projects Releases Wiki Activity
2,761 Commits 141 Branches 65 Tags
Commit Graph

152 Commits

Author SHA1 Message Date
Ross Wightman
d7d3538335 Add so400m model size for test, few tweaks. 2025-05-23 18:29:30 -07:00
Ross Wightman
7bfe606d9f Merge remote-tracking branch 'origin/main' into naflex 2025-05-23 09:41:49 -07:00
Ross Wightman
f001b15ed3 NaFlex random erasing performance improvements, python loops were slow. Remove subregion mode, not going to be worth it. 2025-05-20 17:03:46 -07:00
Ross Wightman
7624389fc9 Mixup cleanup, add prob support and train script integration. Add working loader based patch compatible RandomErasing for NaFlex mode. 2025-05-20 14:38:50 -07:00
Ross Wightman
8fcbceb609 Add a WIP NaFlex compatible mixup/cutmix for testing 2025-05-10 14:59:37 -07:00
Ryan Ramos
81900a6bae remove download argument from torch_kwargs 2025-05-09 07:34:32 -07:00
Ross Wightman
e2073e32d0 Move NaFlexCollate with dataset, remove stand alone collate_fn and remove redundancy 2025-04-29 10:44:46 -07:00
Ross Wightman
3dc90ed7a7 Add naflex loader support to validate.py, fix bug in naflex pos embed add, classic vit weight loading for naflex model 2025-04-25 16:00:54 -07:00
Ross Wightman
13e0f3a4a3 Add loss scale arg, initial distributed loss scale. Maybe fix FX for the model. 2025-04-08 20:47:57 -07:00
Ross Wightman
825edccf19 Type fixes, remove old comments 2025-04-07 21:35:03 -07:00
Ross Wightman
0893f5d296 Initial NaFlex ViT model and training support 2025-04-07 21:27:10 -07:00
Josua Rieder
8d81fdf3d9 Fix typos 2025-01-19 13:39:40 -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
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
2fcf73e580 Add mini imagenet info files 2024-11-25 10:53:28 -08:00
Ross Wightman
3bef09f831 Tweak a few docstrings 2024-11-13 10:12:31 -08:00
Augustin Godinot
7f0c1b1f30 Add trust_remote_code argument to ReaderHfds 2024-11-08 08:16:36 -08:00
Ross Wightman
f5b58e31a2 Allow non train mode for wds reader to operate w/o sample count, exhaust iterator 2024-10-31 16:39:35 -07:00
MengqingCao
37c731ca37 fix device check 2024-10-17 12:38:02 +00:00
MengqingCao
234f975787 add npu support 2024-10-16 07:13:45 +00:00
Ross Wightman
cec70b6779
Merge pull request #2225 from huggingface/small_things 
Small things
 2024-07-25 20:29:13 -07:00
Ross Wightman
34c9fee554 Fix pass through of input / target keys so ImageDataset readers so args work with hfds instead of just hfids (iterable) 2024-07-17 10:11:46 -07:00
Ross Wightman
83c2c2f0c5 Add 'Maybe' PIL / image tensor conversions in case image alread in tensor format 2024-07-08 13:43:51 -07:00
Ross Wightman
3bfd036b58 Add normalize flag to transforms factory, allow return of non-normalized native dtype torch.Tensors 2024-05-13 15:23:25 -07:00
Ross Wightman
286d941923 Add teddy-bear class back to first 1000 classes of imagenet22k_ms_synsets (index 851) 2024-04-09 09:33:08 -07:00
Ross Wightman
7d121ac2ef Small tweak of timm ToTensor for clarity 2024-02-10 14:57:40 -08:00
Ross Wightman
809a9e14e2 Pass train-crop-mode to create_loader/transforms from train.py args 2024-01-24 16:19:02 -08:00
Ross Wightman
2eac2f6955 Fiddling with iterator wrapping for HF ds streaming 2024-01-09 12:41:54 -08:00
Ross Wightman
be0944edae Significant transforms, dataset, dataloading enhancements. 2024-01-08 09:38:42 -08:00
Ross Wightman
40d55ab4bc Add in_chans to data config helper. Fix #2021 2023-11-23 12:44:59 -08:00
Ruslan Baikulov
158bf129c4 Replace deprecated NumPy aliases of builtin types 2023-07-03 22:24:25 +03:00
Ross Wightman
8ce9a2c00a
Merge pull request #1222 from Leoooo333/master 
Fix mixup/one_hot device problem
 2023-05-10 08:59:15 -07:00
Ross Wightman
fd592ec86c Fix an issue with FastCollateMixup still using device 2023-05-10 08:55:38 -07:00
Ross Wightman
f4825a09ef
Merge pull request #212 from bryant1410/patch-1 
Fix MultiEpochsDataLoader when there's no batching
 2023-04-20 07:09:27 -07:00
Ross Wightman
9fcfb8bcc1 Add Microsoft FocalNet specific ('ms') ImageNet-22k classifier layout 2023-03-18 14:57:34 -07:00
Ross Wightman
c30a160d3e Merge remote-tracking branch 'origin/main' into focalnet_and_swin_refactor 2023-03-15 15:58:39 -07:00
Ross Wightman
3a636eee71 Fix #1713 missed assignement in 3-aug level fn, fix few other minor lint complaints in auto_augment.py 2023-03-11 14:32:23 -08:00
Ross Wightman
7266c5c716 Merge branch 'main' into focalnet_and_swin_refactor 2023-02-17 09:20:14 -08:00
Ross Wightman
9c14654a0d Improve support for custom dataset label name/description through HF hub export, via pretrained_cfg 2023-02-08 08:29:20 -08:00
Ross Wightman
0f2803de7a Move ImageNet metadata (aka info) files to timm/data/_info. Add helper classes to make info available for labelling. Update inference.py for first use. 2023-02-06 17:45:03 -08:00
Ross Wightman
e9f1376cde Cleanup resolve data config fns, add 'model' variant that takes model as first arg, make 'args' arg optional in original fn 2023-01-20 14:47:55 -08:00
Ross Wightman
c061d5e401 Allow using class_map functionality w/ IterableDataset (TFDS/WDS) to remap class labels 2023-01-09 16:28:47 -08:00
Ross Wightman
d5aa17e415 Remove print from auto_augment 2022-12-28 17:11:35 -08:00
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. 2022-12-22 21:34:13 -08:00
Ross Wightman
e7da205345 Fix aa min_max level clamp 2022-12-10 16:43:28 -08:00
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 2022-12-10 16:25:50 -08:00
Ross Wightman
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
Ross Wightman
3db4e346e0 Switch TFDS dataset to use INTEGER_ACCURATE jpeg decode by default 2022-12-05 10:21:34 -08:00
Ross Wightman
9da7e3a799 Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate 2022-12-05 10:21:34 -08:00
Ross Wightman
0dadb4a6e9 Initial multi-weight support, handled so old pretraing config handling co-exists with new tags. 2022-12-05 10:21:34 -08:00