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

568 Commits (e39bf6ef591d9fe79986f8732181ea0f39b5c598)
 

Author SHA1 Message Date
Ross Wightman e39bf6ef59
Merge pull request #237 from rwightman/utils_cleanup 
Utils refactor, more cutmix modes / change mode arg
 2020-09-11 13:29:18 -07:00
Ross Wightman 47a7b3b5b1 More flexible mixup mode, add 'half' mode. 2020-09-07 20:03:06 -07:00
Ross Wightman 532e3b417d Reorg of utils into separate modules 2020-09-07 13:58:09 -07:00
Ross Wightman 9ce42d5c5a
Update README.md 2020-09-03 10:48:25 -07:00
Ross Wightman 0729dbe865
Update README.md 2020-09-03 10:48:11 -07:00
Ross Wightman 33f8a1bf36 Updated README, add wide_resnet50_2 and seresnext50_32x4d weights 2020-09-03 10:45:17 -07:00
Ross Wightman 5247eb37a7
Merge pull request #233 from rwightman/torchamp 
Native Torch AMP and channels_last support for train.py and validate.py
 2020-09-02 17:42:41 -07:00
Ross Wightman 751b0bba98 Add global_pool (--gp) arg changes to allow passing 'fast' easily for train/validate to avoid channels_last issue with AdaptiveAvgPool 2020-09-02 16:13:47 -07:00
Ross Wightman 9c297ec67d Cleanup Apex vs native AMP scaler state save/load. Cleanup CheckpointSaver a bit. 2020-09-02 15:12:59 -07:00
Ross Wightman 80c9d9cc72 Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast' 2020-09-02 09:11:48 -07:00
Ross Wightman 90a01f47d1 hrnet features_only pretrained weight loading issue. Fix #232. 2020-09-01 17:37:55 -07:00
Ross Wightman 110a7c4982 AdaptiveAvgPool2d -> mean((2,3)) for all SE/attn layers to avoid NaN with AMP + channels_last layout. See https://github.com/pytorch/pytorch/issues/43992 2020-09-01 16:05:32 -07:00
Ross Wightman c2cd1a332e Improve torch amp support and add channels_last support for train/validate scripts 2020-08-31 17:58:16 -07:00
Ross Wightman 1d34a0a851 Merge branch 'master' of https://github.com/tgisaturday/pytorch-image-models into torchamp 2020-08-30 18:16:47 -07:00
Ross Wightman 6d158adfe9
Update README.md 2020-08-26 15:15:51 -07:00
datamining99 5f563ca4df fix save_checkpoint bug with native amp 2020-08-22 11:31:50 +09:00
datamining99 d98967ed5d add support for native torch AMP in torch 1.6 2020-08-22 09:44:23 +09:00
Ross Wightman 470220b1f4 Fix MobileNetV3 crash with global_pool='', output consistent with other models but not equivalent due to efficient head. 2020-08-18 14:11:30 -07:00
Ross Wightman fc8b8afb6f Fix a silly bug in Sample version of EvoNorm missing x* part of swish, update EvoNormBatch to accumulated unbiased variance. 2020-08-13 18:25:01 -07:00
Ross Wightman fa26f6c1cf
Update README.md 2020-08-12 23:26:59 -07:00
Ross Wightman f614df7921 Bump version to 0.2.1 and update README 2020-08-12 18:05:07 -07:00
Ross Wightman b423bc8362
Merge pull request #218 from rwightman/cutmix 
CutMix + MixUp overhaul
 2020-08-12 17:17:41 -07:00
Ross Wightman 8c9814e3f5 Final cleanup of mixup/cutmix. Element/batch modes working with both collate (prefetcher active) and without prefetcher. 2020-08-12 17:01:32 -07:00
Ross Wightman 0f5d9d8166 Add CSPResNet50 weights, 79.6 top-1 at 256x256 2020-08-12 11:20:11 -07:00
Ross Wightman 0734c0d187 Update test workflow 2020-08-11 19:04:37 -07:00
Ross Wightman b1b6e7c361 Fix a few more issues related to #216 w/ TResNet (space2depth) and FP16 weights in wide resnets. Also don't completely dump pretrained weights in in_chans != 1 or 3 cases. 2020-08-11 18:57:47 -07:00
Ross Wightman 512b2dd645 Add new EfficientNet-B3 and RegNetY-3.2GF weights, both just over 82 top-1 2020-08-11 14:18:51 -07:00
Ross Wightman 6890300877 Add DropPath (stochastic depth) to RegNet 2020-08-11 14:08:53 -07:00
Ross Wightman 47794d2c59
Merge pull request #216 from yu4u/fix_default_cfgs 
Fix default_cfgs for first conv
 2020-08-11 12:34:19 -07:00
Ross Wightman cd23f55397 Fix mixed prec issues with new mixup code 2020-08-11 12:17:43 -07:00
Yusuke Uchida e717250ed4 remove comments 2020-08-11 23:33:22 +09:00
Yusuke Uchida f6b56602f9 fix test_model_default_cfgs 2020-08-11 23:23:57 +09:00
Ross Wightman f471c17c9d More cutmix/mixup overhaul, ready to kick-off some trials. 2020-08-11 00:10:33 -07:00
Ross Wightman 078a51dbac
Merge pull request #214 from MohamedAliRashad/patch-1 
mobilenetv3_100 doesn't exist
 2020-08-08 16:15:22 -07:00
Ross Wightman d5145fa4d5 Change default_cfg names for senet to include the legacy and match model names 2020-08-08 11:12:58 -07:00
Mohamed Rashad 44d8ecc6e1
mobilenetv3_100 doesn't exist 2020-08-08 14:10:40 +02:00
Ross Wightman 92f2d0d65d Merge branch 'master' into cutmix. Fixup a few issues. 2020-08-07 15:59:52 -07:00
Ross Wightman 6e9d6172c8 A few typos and missed updates in changelog 2020-08-05 22:19:59 -07:00
Ross Wightman 57510fd5b2 Fix some documentation rendering issues 2020-08-05 17:27:52 -07:00
Ross Wightman 80c3051f5d
Merge pull request #175 from rwightman/features 
Feature extraction interface, model cleanup, 'real labels' validation support
 2020-08-05 17:00:43 -07:00
Ross Wightman 1a15502fa4 mkdocs sortable tables.js 2020-08-05 16:57:13 -07:00
Ross Wightman 1696499ce5 Bump version to 0.2.0, ready to roll (I think) 2020-08-05 16:55:18 -07:00
Ross Wightman e62758cf4f More documentation updates, fix a typo 2020-08-05 15:59:31 -07:00
Ross Wightman 5e333b899f README / doc tweaks 2020-08-05 13:17:39 -07:00
Ross Wightman dfe80414a6 Add bool arg helper 2020-08-05 13:17:23 -07:00
Ross Wightman fa28067704 Add more augmentation arguments, including a no_aug disable flag. Fix #209 2020-08-05 13:16:44 -07:00
Ross Wightman e3f58fc90c Continuing README and documentation updates 2020-08-05 10:38:35 -07:00
Ross Wightman e3c11a36dc Start updating README and docs 2020-08-04 16:55:02 -07:00
Ross Wightman b1f1a54de9 More uniform treatment of classifiers across all models, reduce code duplication. 2020-08-03 22:18:24 -07:00
Ross Wightman 9806f3e1ff autosquash github workflow didn't work out, removing 2020-08-03 17:23:57 -07:00