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
Ross Wightman
13e8da2b46
SelectKernel split_input works best when input channels split like grouped conv, but output is full width. Disable zero_init for SK nets, seems a bad combo.
2020-02-07 22:42:04 -08:00
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Bump version for PyPi update, fix few out of date README items/mistakes, add README updates for TF EfficientNet-B8 (RandAugment)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
7d07ebb660
Adding some configs to sknet, incl ResNet50 variants from 'Compounding ... Assembled Techniques' paper and original SKNet50
2020-02-01 23:28:48 -08:00
Ross Wightman
a9d2424fd1
Add separate zero_init_last_bn function to support more block variety without a mess
2020-02-01 22:11:00 -08:00
Ross Wightman
355aa152d5
Just leave it float for now, will look at fp16 later. Remove unused reference code.
2020-02-01 22:11:00 -08:00
Ross Wightman
ef457555d3
BlockDrop working on GPU
2020-02-01 22:11:00 -08:00
Ross Wightman
3ff19079f9
Missed nn_ops.py from last commit
2020-02-01 22:11:00 -08:00
Ross Wightman
9f11b4e8a2
Add ConvBnAct layer to parallel integrated SelectKernelConv, add support for DropPath and DropBlock to ResNet base and SK blocks
2020-02-01 22:11:00 -08:00
Ross Wightman
cefc9b7761
Move SelectKernelConv to conv2d_layers and more
...
* always apply attention in SelectKernelConv, leave MixedConv for no attention alternative
* make MixedConv torchscript compatible
* refactor first/previous dilation name to make more sense in ResNet* networks
2020-02-01 22:11:00 -08:00
Ross Wightman
9abe610931
Used wrong channel var for split
2020-02-01 22:11:00 -08:00
Ross Wightman
58e28dc7e7
Move Selective Kernel blocks/convs to their own sknet.py file
2020-02-01 22:11:00 -08:00
Ross Wightman
a93bae6dc5
A SelectiveKernelBasicBlock for more experiments
2020-02-01 22:11:00 -08:00
Ross Wightman
ad087b4b17
Missed bias=False in selection conv
2020-02-01 22:11:00 -08:00
Ross Wightman
c8b3d6b81a
Initial impl of Selective Kernel Networks. Very much a WIP.
2020-02-01 22:11:00 -08:00
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
