0e16d4e9fb
Add benchmark.py script, and update optimizer factory to be more friendly to use outside of argparse interface.
4 years ago
4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
4 years ago
8563609b28
Update notes in ScaledStdConv impl
4 years ago
678ba4e0a2
Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.
4 years ago
9de2ec5e44
Update README for AGC and bump version to 0.4.4
4 years ago
4f49b94311
Initial AGC impl. Still testing.
4 years ago
5f9aff395c
Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing.
4 years ago
d86dbe45c2
Update README.md and few more comments
4 years ago
0d253e2c5e
Fix issue with nfnet tests, bit more cleanup.
4 years ago
cb06c7a910
Add NFNet-F models and tweak existing NF models.
4 years ago
e4de077021
Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288).
4 years ago
d8e69206be
Merge pull request #419 from rwightman/byob_vgg_models
...
More models, GPU-Efficient Nets, RepVGG, classic VGG, and flexible Byob backbone.
4 years ago
ca9b078ac7
Update README.md and docs. Version bumped to 0.4.3
4 years ago
6853b07bbd
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
4 years ago
0356e773f5
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
4 years ago
94ca140b67
update collections.abc import
4 years ago
b4e216e377
Fix a few small things.
4 years ago
dc85e5a237
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
4 years ago
1bcc69e0ad
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354 .
4 years ago
9811e229f7
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
4 years ago
a39c3ee216
Merge branch 'master' into eca-weights
4 years ago
e9d6fe293c
Update README for new weights. Version 0.4.2
4 years ago
666de85cf1
Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414
4 years ago
3b57490a63
Fix some half removed resnet model defs, pooling for ecaresnet269d
4 years ago
68a4144882
Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg.
4 years ago
b9843f954b
Merge pull request #282 from tigert1998/patch-1
...
Add symbolic for SwishJitAutoFn to support onnx
4 years ago
7a4be5c035
add operator HardSwishJitAutoFn export to onnx
4 years ago
4203efa36d
Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py.
4 years ago
f0e65e37b7
Fix NF-ResNet101 model defs
4 years ago
2c988c3b6e
Update README.md for NF-nets, bump version to 0.4.1 for merge
4 years ago
2de54d174a
Fix pool size defs for NFNet models, add a comment.
4 years ago
90980de4a9
Fix up a few details in NFResNet models, managed stable training. Add support for gamma gain to be applied in activation or ScaleStdConv. Some tweaks to ScaledStdConv.
4 years ago
5a8e1e643e
Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.
4 years ago
38d8f67570
Fix potential issue with change to num_classes arg in train/validate.py defaulting to None (rely on model def / default_cfg)
4 years ago
587780e56b
Update README.md and bump version to 0.4.0
4 years ago
bb50ac4708
Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args.
4 years ago
c16e965037
Add some ViT comments and fix a few minor issues.
4 years ago
22748f1a2d
Convert samples/targets in ParserImageInTar to numpy arrays, slightly less mem usage for massive datasets. Add a few more se/eca model defs to resnet.py
4 years ago
5d4c3d0af3
Add enhanced ParserImageInTar that can read images from tars within tars, folders with multiple tars, etc. Additional comment cleanup.
4 years ago
55f7dfa9ea
Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing
4 years ago
d55bcc0fee
Finishing adding stochastic depth support to BiT ResNetV2 models
4 years ago
855d6cc217
More dataset work including factories and a tensorflow datasets (TFDS) wrapper
...
* Add parser/dataset factory methods for more flexible dataset & parser creation
* Add dataset parser that wraps TFDS image classification datasets
* Tweak num_classes handling bug for 21k models
* Add initial deit models so they can be benchmarked in next csv results runs
4 years ago
20516abc18
Fix some broken tests for ResNetV2 BiT models
4 years ago
59ec7e6a53
Merge branch 'master' into imagenet21k_datasets_more
4 years ago
e7a9ddf982
Merge pull request #334 from kecsap/links
...
Follow symbolic links during dataset scanning
4 years ago
7cae7e7035
Follow links during dataset scanning
4 years ago
c96e9f99a0
Update version to 0.3.3
4 years ago
4e2533db77
Add 320x320 model default cfgs for 101D and 152D ResNets. Add SEResNet-152D weights and 320x320 cfg.
4 years ago
0167f749d3
Remove some old __future__ imports
4 years ago
e35e9760a6
More work on dataset / parser split and imagenet21k (tar) support
4 years ago
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
4 years ago
231d04e91a
ResNetV2 pre-act and non-preact model, w/ BiT pretrained weights and support for ViT R50 model. Tweaks for in21k num_classes passing. More to do... tests failing.
4 years ago
de6046e213
Initial commit for dataset / parser reorg to support additional datasets / types
4 years ago
392595c7eb
Add pool_size to default cfgs for new models to prevent tests from failing. Add explicit 200D_320 model entrypoint for next benchmark run.
4 years ago
b1f1228a41
Add ResNet101D, 152D, and 200D weights, remove meh 66d model
4 years ago
7c56c718f3
Configure create_optimizer with args.opt_args
...
Closes #301
4 years ago
9a25fdf3ad
Merge pull request #297 from rwightman/ema_simplify
...
Simplified JIT compatible Ema module. Fixes for SiLU export and torchscript training w/ Linear layer.
4 years ago
de15b43865
Fix a bug with accuracy retrieving from RealLabels
4 years ago
cd72e66eff
Bug in last mod for features_only default_cfg
4 years ago
867a0e5a04
Add default_cfg back to models wrapped in feature extraction module as per discussion in #294 .
4 years ago
4ca52d73d8
Add separate set and update method to ModelEmaV2
4 years ago
2ed8f24715
A few more changes for 0.3.2 maint release. Linear layer change for mobilenetv3 and inception_v3, support no bias for linear wrapper.
4 years ago
6504a42832
Version 0.3.2
4 years ago
460eba7f24
Work around casting issue with combination of native torch AMP and torchscript for Linear layers
4 years ago
5f4b6076d8
Fix inplace arg compat for GELU and PreLU via activation factory
4 years ago
fd962c4b4a
Native SiLU (Swish) op doesn't export to ONNX
4 years ago
27bbc70d71
Add back old ModelEma and rename new one to ModelEmaV2 to avoid compat breaks in dependant code. Shuffle train script, add a few comments, remove DataParallel support, support experimental torchscript training.
4 years ago
43f2500c26
Add symbolic for SwishJitAutoFn to support onnx
4 years ago
9214ca0716
Simplifying EMA...
4 years ago
53aeed3499
ver 0.3.1
4 years ago
30ab4a1494
Fix issue in optim factory with sgd / eps flag. Bump version to 0.3.1
4 years ago
741572dc9d
Bump version to 0.3.0 for pending PyPi push
4 years ago
b401952caf
Add newly added vision transformer large/base 224x224 weights ported from JAX official repo
4 years ago
61200db0ab
in_chans=1 working w/ pretrained weights for vision_transformer
4 years ago
e90edce438
Support native silu activation (aka swish). An optimized ver is available in PyTorch 1.7.
4 years ago
da6cd2cc1f
Fix regression for pretrained classifier loading when using entrypt functions directly
4 years ago
f591e90b0d
Make sure num_features attr is present in vit models as with others
4 years ago
4a3df7842a
Fix topn metric view regression on PyTorch 1.7
4 years ago
f944242cb0
Fix #262 , num_classes arg mixup. Make vision_transformers a bit closer to other models wrt get/reset classfier/forward_features. Fix torchscript for ViT.
4 years ago
736f209e7d
Update vision transformers to be compatible with official code. Port official ViT weights from jax impl.
4 years ago
477a78ed81
Fix optimizer factory regressin for optimizers like sgd/momentum that don't have an eps arg
4 years ago
27a93e9de7
Improve test crop for ViT models. Small now 77.85, added base weights at 79.35 top-1.
4 years ago
d4db9e7977
Add small vision transformer weights. 77.42 top-1.
4 years ago
27fadaa922
asymmetric_loss
4 years ago
f31933cb37
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
4 years ago
a4d8fea61e
Add model based wd skip support. Improve cross version compat of optimizer factory. Fix #247
4 years ago
80078c47bb
Add Adafactor and Adahessian optimizers, cleanup optimizer arg passing, add gradient clipping support.
4 years ago
fcb6258877
Add missing leaky_relu layer factory defn, update Apex/Native loss scaler interfaces to support unscaled grad clipping. Bump ver to 0.2.2 for pending release.
4 years ago
e8e2d9cabf
Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.
4 years ago
e8ca45854c
More models in sotabench, more control over sotabench run, dataset filename extraction consistency
4 years ago
9c406532bd
Add EfficientNet-EdgeTPU-M (efficientnet_em) model trained natively in PyTorch. More sotabench fiddling.
4 years ago
c40384f5bd
Add ResNet weights. 80.5 (top-1) ResNet-50-D, 77.1 ResNet-34-D, 72.7 ResNet-18-D.
4 years ago
47a7b3b5b1
More flexible mixup mode, add 'half' mode.
4 years ago
532e3b417d
Reorg of utils into separate modules
4 years ago
33f8a1bf36
Updated README, add wide_resnet50_2 and seresnext50_32x4d weights
4 years ago
751b0bba98
Add global_pool (--gp) arg changes to allow passing 'fast' easily for train/validate to avoid channels_last issue with AdaptiveAvgPool
4 years ago
9c297ec67d
Cleanup Apex vs native AMP scaler state save/load. Cleanup CheckpointSaver a bit.
4 years ago
80c9d9cc72
Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast'
4 years ago
90a01f47d1
hrnet features_only pretrained weight loading issue. Fix #232 .
4 years ago
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
4 years ago
Ross Wightman