7a4be5c035
add operator HardSwishJitAutoFn export to onnx
4 years ago
f0e65e37b7
Fix NF-ResNet101 model defs
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
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
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
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
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
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
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
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
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
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
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
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
f31933cb37
Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.
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
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
470220b1f4
Fix MobileNetV3 crash with global_pool='', output consistent with other models but not equivalent due to efficient head.
4 years ago
fc8b8afb6f
Fix a silly bug in Sample version of EvoNorm missing x* part of swish, update EvoNormBatch to accumulated unbiased variance.
4 years ago
0f5d9d8166
Add CSPResNet50 weights, 79.6 top-1 at 256x256
4 years ago
hwangdeyu