780860d140
Add norm_act factory method, move JIT of norm layers to factory
4 years ago
14edacdf9a
DenseNet converted to support ABN (norm + act) modules. Experimenting with EvoNorm, IABN
4 years ago
022ed001f3
Update DenseNet to latest in Torchvision (torchscript compat, checkpointing, proper init). Start adding ehanced configurability, stem options...
4 years ago
a7ebe09029
Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.
...
Make small code refactoring
4 years ago
f0eb021620
Replace all None by nn.Identity() in HRNet modules
4 years ago
8d8677e03b
Fix #139 . Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.
4 years ago
9c15d57505
added efficientnet pruned weights
4 years ago
ea300709f0
Fix model create fn not passing num_classes through. Fix #135
4 years ago
2c438c4e0d
Merge branch 'master' of github.com:rwightman/pytorch-models
4 years ago
2681a8d618
Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop
4 years ago
9590f301a9
Merge branch 'blur' of https://github.com/VRandme/pytorch-image-models into VRandme-blur
4 years ago
a5220ad3aa
Merge pull request #125 from Separius/patch-1
...
fix typo in eca
4 years ago
0834fbc01c
Move pruned model adapt strings to separate txt files. A few minor formatting alignment tweaks.
4 years ago
ba793f5c1c
Merge branch 'adding_ECA_resnet' of https://github.com/yoniaflalo/pytorch-image-models into yoniaflalo-adding_ECA_resnet
4 years ago
07f19dd699
added eca resnet
4 years ago
be7c784d21
Small TResNet simplification, just use SelectAdaptivePool, don't notice any perf difference
4 years ago
e3a98171b2
Remove some CRLF that made it into TResNet merge
4 years ago
0004f37d25
Some TResNet cleanup.
...
* allow use of global pool arg, test-time-pooling
* clean checkpoints to just contain state dict, add 448 res checkpoints
* support DataParallel via lazy filter creation for JIT Downsample
* some minor formatting (mostly alignment) preferences
4 years ago
20290b5b56
fix typo in eca
4 years ago
ebf82b84ac
Merge pull request #122 from mrT23/master
...
TResNet models
4 years ago
bdb165a8a4
Merge changes in feature extraction interface to MobileNetV3
...
Experimental feature extraction interface seems to be changed
a little bit with the most up to date version apparently found
in EfficientNet class. Here these changes are added to
MobileNetV3 class to make it support it and work again, too.
4 years ago
8a63c1add8
finalizing
4 years ago
6209146738
TResNet models
4 years ago
1a8f5900ab
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
4 years ago
06a50a94a8
Fix minor typos in create_attn.py and resnet.py
...
'eca'->'ceca'
and
doest not-> does not
4 years ago
1a9ab07307
One too many changes at a time, fix missing C
4 years ago
f17b42bc33
Blur filter no longer a buffer
4 years ago
6cdeca24a3
Some cleanup and fixes for initial BlurPool impl. Still some testing and tweaks to go...
4 years ago
acd1b6cccd
Implement Functional Blur on resnet.py
...
1. add ResNet argument blur=''
2. implement blur for maxpool and strided convs in downsampling blocks
4 years ago
ce3d82b58b
Update blurpool.py
...
clean up code for PR
4 years ago
3a287a6e76
Create blurpool.py
...
Initial implementation of blur layer.
currently tests as correct against Downsample of original github
4 years ago
c99a5abed4
Merge pull request #115 from rwightman/mobilenetv2-experiment
...
MobileNet-V2 experiments
4 years ago
e34074b4da
Add final weights for MobileNet-V2 experiments
4 years ago
a6a5565de7
Fiddling...
4 years ago
5a16c533ff
Add better resnext50_32x4d weights trained by andravin
4 years ago
bc998cad91
Experimenting with some MobileNetV2 variations to compare against EfficientNet-Lite
4 years ago
3406e582cf
Add EfficientNet-Lite results, update README
4 years ago
bd05258f7b
EfficientNet-Lite model added w/ converted checkpoints, validation in progress...
4 years ago
56e2ac3a6d
Merge pull request #94 from rwightman/lr_noise
...
Learning rate noise, MobileNetV3 weights, and activate MobileNetV3/EfficientNet weight init change
4 years ago
c16f25ced2
Add MobileNetV3 Large weights, results, update README and sotabench for merge
4 years ago
c60069c1eb
Annotate types on drop fns to avoid torchscript error
4 years ago
9fee316752
Enable fixed fanout calc in EfficientNet/MobileNetV3 weight init by default. Fix #84
4 years ago
43225d110c
Unify drop connect vs drop path under 'drop path' name, switch all EfficientNet/MobilenetV3 refs to 'drop_path'. Update factory to handle new drop args.
4 years ago
f1d5f8a6c4
Update comments for Selective Kernel and DropBlock/Path impl, add skresnet34 weights
4 years ago
569419b38d
Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch
4 years ago
53c47479c4
Batch validation batch size adjustment, tweak L2 crop pct
4 years ago
08553e16b3
Merge branch 'master' into attention
4 years ago
fa38f24967
Update SK network configs, add weights for skresnet8 and skresnext50
4 years ago
ba15ca47e8
Add ported EfficientNet-L2, B0-B7 NoisyStudent weights from TF TPU
4 years ago
5e6dbbaf30
Add CBAM for experimentation
4 years ago
d725991870
Remove debug print from ECA module
4 years ago
2a7d256fd5
Re-enable mem-efficient/jit activations after torchscript tests
4 years ago
f902bcd54c
Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
...
* select_conv2d -> create_conv2d
* added create_attn to create attention module from string/bool/module
* factor padding helpers into own file, use in both conv2d_same and avg_pool2d_same
* add some more test eca resnet variants
* minor tweaks, naming, comments, consistency
4 years ago
a99ec4e7d1
A bunch more layer reorg, splitting many layers into own files. Improve torchscript compatibility.
4 years ago
13746a33fc
Big move, layer modules and fn to timm/models/layers
4 years ago
f54612f648
Merge branch 'select_kernel' into attention
4 years ago
4defbbbaa8
Fix module name mistake, start layers sub-package
4 years ago
7011cd0902
A little bit of ECA cleanup
4 years ago
46471df7b2
Merge pull request #82 from VRandme/eca
...
ECA-Net Efficient Channel Attention
4 years ago
d0eb59ef46
Remove unused default_init for EfficientNets, experimenting with fanout calc for #84
4 years ago
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
4 years ago
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.
4 years ago
6db087a1ff
Merge remote-tracking branch 'upstream/master' into eca
4 years ago
904c618040
Update EcaModule.py
...
Make pylint happy
(commas, unused imports, missed imports)
4 years ago
db91ba053b
EcaModule(CamelCase)
...
CamelCased EcaModule.
Renamed all instances of ecalayer to EcaModule.
eca_module.py->EcaModule.py
4 years ago
5c4991a088
Add PyTorch trained EfficientNet-ES weights from Andrew Lavin
4 years ago
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
4 years ago
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
4 years ago
7d07ebb660
Adding some configs to sknet, incl ResNet50 variants from 'Compounding ... Assembled Techniques' paper and original SKNet50
4 years ago
a9d2424fd1
Add separate zero_init_last_bn function to support more block variety without a mess
4 years ago
355aa152d5
Just leave it float for now, will look at fp16 later. Remove unused reference code.
4 years ago
ef457555d3
BlockDrop working on GPU
4 years ago
3ff19079f9
Missed nn_ops.py from last commit
4 years ago
9f11b4e8a2
Add ConvBnAct layer to parallel integrated SelectKernelConv, add support for DropPath and DropBlock to ResNet base and SK blocks
4 years ago
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
4 years ago
9abe610931
Used wrong channel var for split
4 years ago
58e28dc7e7
Move Selective Kernel blocks/convs to their own sknet.py file
4 years ago
a93bae6dc5
A SelectiveKernelBasicBlock for more experiments
4 years ago
ad087b4b17
Missed bias=False in selection conv
4 years ago
c8b3d6b81a
Initial impl of Selective Kernel Networks. Very much a WIP.
4 years ago
91534522f9
Add newly added TF ported EfficientNet-B8 weights (RandAugment)
4 years ago
12dbc74742
New ResNet50 JSD + RandAugment weights
4 years ago
2f41905ba5
Update ResNet50 weights to AuxMix trained 78.994 top-1. A few commentes re 'tiered_narrow' tn variant.
5 years ago
d9a6a9d0af
Merge pull request #74 from rwightman/augmix-jsd
...
AugMix, JSD loss, SplitBatchNorm (Auxiliary BN), and more
5 years ago
3eb4a96eda
Update AugMix, JSD, etc comments and references
5 years ago
a28117ea46
Add tiered narrow ResNet (tn) and weights for seresnext26tn_32x4d
5 years ago
833066b540
A few minor things in SplitBN
5 years ago
7547119891
Add SplitBatchNorm. AugMix, Rand/AutoAugment, Split (Aux) BatchNorm, Jensen-Shannon Divergence, RandomErasing all working together
5 years ago
ec0dd4053a
Add updated RandAugment trained EfficientNet-B0 trained weights from @michaelklachko
5 years ago
40fea63ebe
Add checkpoint averaging script. Add headers, shebangs, exec perms to all scripts
5 years ago
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
5 years ago
f96b3e5e92
InceptionResNetV2 torchscript compatible
5 years ago
19d93fe454
Add selecsls60 weights
5 years ago
0062c15fb0
Update checkpoint url with modelzoo compatible ones.
5 years ago
b5315e66b5
Streamline SelecSLS model without breaking checkpoint compat. Move cfg handling out of model class. Update feature/pooling behaviour to match current.
5 years ago
d59a756c16
Run PyCharm autoformat on selecsls and change mix cap variables and model names to all lower
5 years ago
fb3a0f4bb8
Merge pull request #65 from mehtadushy/selecsls
...
Incorporate SelecSLS Models
5 years ago
19fc205a4d
Update comments on the new SE-ResNeXt26 models
5 years ago
acc3ed2b8c
Add EfficientNet-B3 weights, trained from scratch with RA.
5 years ago
2404361f62
correct asset paths
5 years ago
Ross Wightman
Vyacheslav Shults
AFLALO, Jonathan Isaac
Ross Wightman
Sepehr Sameni
Alexey Chernov
talrid
Chris Ha
Dushyant Mehta