305 Commits

Author SHA1 Message Date
Chris Ha
e6a762346a Implement Adaptive Kernel selection
When channel size is given,
calculate adaptive kernel size according to original paper.
Otherwise use the given kernel size(k_size), which defaults to 3
2020-02-09 11:58:03 +09:00
Chris Ha
6db087a1ff Merge remote-tracking branch 'upstream/master' into eca 2020-02-07 19:36:35 +09:00
Chris Ha
904c618040 Update EcaModule.py
Make pylint happy
(commas, unused imports, missed imports)
2020-02-07 19:36:18 +09:00
Chris Ha
db91ba053b EcaModule(CamelCase)
CamelCased EcaModule.
Renamed all instances of ecalayer to EcaModule.
eca_module.py->EcaModule.py
2020-02-07 19:28:07 +09:00
Ross Wightman
5eb0e363a6
Update README.md 2020-02-06 12:56:46 -08:00
Ross Wightman
5c4991a088 Add PyTorch trained EfficientNet-ES weights from Andrew Lavin 2020-02-06 12:53:55 -08:00
Chris Ha
d04ff95eda Merge branch 'master' into eca 2020-02-06 22:44:52 +09:00
Chris Ha
d63ae121d5 Clean up eca_module code
functionally similar
adjusted rwightman's version of reshaping and viewing.
Use F.pad for circular eca version for cleaner code
2020-02-06 22:44:33 +09:00
Chris Ha
b0d45fd09c Merge remote-tracking branch 'upstream/master' 2020-02-06 22:00:37 +09:00
Ross Wightman
d66819d1f3 Indentation mistake. Fixes #81 2020-02-04 22:56:00 -08:00
Ross Wightman
65cda1c63f
Merge pull request #83 from andravin/validation-batch-size-multiplier
Added commandline argument validation-batch-size-multiplier.
2020-02-04 22:49:42 -08:00
Chris Ha
f87fcd7e88 Implement Eca modules
implement ECA module by
1. adopting original eca_module.py into models folder
2. adding use_eca layer besides every instance of SE layer
2020-02-04 23:15:29 +09:00
Chris Ha
697e05cb3e Merge remote-tracking branch 'upstream/master' 2020-02-04 21:02:55 +09:00
Andrew Lavin
b72013def8 Added commandline argument validation-batch-size-multiplier with default set to 1. 2020-02-04 01:02:27 -08:00
Ross Wightman
4808b3c32f Bump version for PyPi update, fix few out of date README items/mistakes, add README updates for TF EfficientNet-B8 (RandAugment) 2020-02-03 11:44:17 -08:00
Ross Wightman
5c85389e26
Update README.md 2020-02-02 20:01:26 -08:00
Ross Wightman
820b73d280
Update README.md 2020-02-02 19:38:10 -08:00
Ross Wightman
82c0a2ff12
Update README.md
Fix relative paths (I think)
2020-02-02 19:37:18 -08:00
Ross Wightman
1ffd2d0694
Add results/README.md 2020-02-02 19:35:44 -08:00
Chris Ha
89a32454e1 Merge remote-tracking branch 'upstream/master' 2020-02-02 23:05:49 +09:00
Ross Wightman
fd98fb33c5 Update sotabench with tf_efficientnet_b8 model 2020-02-01 18:12:25 -08:00
Ross Wightman
7c88356682 Add update results on ImageNet validation, ImageNetV2, ImageNet-A, and ImageNet-Sketch for all models 2020-02-01 18:10:13 -08:00
Ross Wightman
1daa303744 Add support to Dataset for class id mapping file, clean up a bit of old logic. Add results file arg for validation and update script. 2020-02-01 18:07:32 -08:00
Ross Wightman
91534522f9 Add newly added TF ported EfficientNet-B8 weights (RandAugment) 2020-02-01 18:01:14 -08:00
Ross Wightman
82dd60b33c Rename results files for more clarity 2020-01-31 23:00:02 -08:00
Ross Wightman
5b7cc16ac9 Add warning about using sync-bn with zero initialized BN layers. Fixes #54 2020-01-31 11:44:24 -08:00
Ross Wightman
b18c19901e
Update README.md
Typo
2020-01-31 10:59:31 -08:00
Ross Wightman
12dbc74742 New ResNet50 JSD + RandAugment weights 2020-01-31 10:55:54 -08:00
Chris Ha
0697ab183b Update .gitignore 2020-01-30 20:40:55 +09:00
Ross Wightman
e39aae56b4
Update README.md
Fix typo
2020-01-13 17:49:49 -08:00
Ross Wightman
7a17ee9c3b Update README.md 2020-01-12 18:16:36 -08:00
Ross Wightman
e42503e1d0 Update sotabench 2020-01-12 18:00:12 -08:00
Ross Wightman
2f41905ba5 Update ResNet50 weights to AuxMix trained 78.994 top-1. A few commentes re 'tiered_narrow' tn variant. 2020-01-12 17:55:58 -08:00
Ross Wightman
cc0b1f4130 Add support to clean_checkpoint.py to remove aux_bn weights/biases from SplitBatchNorm 2020-01-12 17:52:19 -08:00
Ross Wightman
2a88412413
Update README.md 2020-01-11 12:08:15 -08:00
Ross Wightman
d9a6a9d0af
Merge pull request #74 from rwightman/augmix-jsd
AugMix, JSD loss, SplitBatchNorm (Auxiliary BN), and more
2020-01-11 12:04:29 -08:00
Ross Wightman
3eb4a96eda Update AugMix, JSD, etc comments and references 2020-01-11 12:02:05 -08:00
Ross Wightman
a28117ea46 Add tiered narrow ResNet (tn) and weights for seresnext26tn_32x4d 2020-01-11 11:29:01 -08:00
Ross Wightman
cfa951bceb
Update README.md 2020-01-07 08:52:12 -08:00
Ross Wightman
833066b540 A few minor things in SplitBN 2020-01-05 20:07:03 -08:00
Ross Wightman
7547119891 Add SplitBatchNorm. AugMix, Rand/AutoAugment, Split (Aux) BatchNorm, Jensen-Shannon Divergence, RandomErasing all working together 2020-01-05 19:58:59 -08:00
Ross Wightman
2e955cfd0c Update RandomErasing with some improved arg names, tweak to aspect range 2020-01-05 14:31:48 -08:00
Ross Wightman
3cc0f91e23 Fix augmix variable name scope overlap, default non-blended mode 2020-01-05 14:27:27 -08:00
Ross Wightman
7622015258
Update README.md 2020-01-04 11:51:38 -08:00
Ross Wightman
ec0dd4053a Add updated RandAugment trained EfficientNet-B0 trained weights from @michaelklachko 2020-01-03 17:18:46 -08:00
Ross Wightman
8662454bd7 Plural for averaging script. 2020-01-03 15:00:20 -08:00
Ross Wightman
40fea63ebe Add checkpoint averaging script. Add headers, shebangs, exec perms to all scripts 2020-01-03 14:57:46 -08:00
Ross Wightman
4666cc9aed Add --pin-mem arg to enable dataloader pin_memory (showing more benefit in some scenarios now), also add --torchscript arg to validate.py for testing models with jit.script 2020-01-02 16:22:06 -08:00
Ross Wightman
53001dd292 ResNet / Res2Net additions:
* ResNet torchscript compat
* output_stride arg supported to limit network stride via dilations (support for dilation added to Res2Net)
* allow activation layer to be changed via act_layer arg
2020-01-01 17:15:56 -08:00
Ross Wightman
f96b3e5e92 InceptionResNetV2 torchscript compatible 2020-01-01 17:13:37 -08:00