Ross Wightman cf5fec5047 Cleanup experimental vit weight init a bit

2021-03-20 09:44:24 -07:00

..

layers

Cleanup experimental vit weight init a bit

2021-03-20 09:44:24 -07:00

pruned

…

__init__.py

Initial AGC impl. Still testing.

2021-02-15 23:22:44 -08:00

byobnet.py

Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.

2021-02-10 14:40:29 -08:00

cspnet.py

Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()

2021-02-23 13:15:52 -08:00

densenet.py

More uniform treatment of classifiers across all models, reduce code duplication.

2020-08-03 22:18:24 -07:00

dla.py

More uniform treatment of classifiers across all models, reduce code duplication.

2020-08-03 22:18:24 -07:00

dpn.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

efficientnet_blocks.py

Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414

2021-02-07 22:10:18 -08:00

efficientnet_builder.py

Merge branch 'logger' into features. Change 'logger' to '_logger'.

2020-07-27 18:00:46 -07:00

efficientnet.py

Bug in last mod for features_only default_cfg

2020-12-03 12:33:01 -08:00

factory.py

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.

2020-12-28 16:59:15 -08:00

features.py

…

gluon_resnet.py

fix test_model_default_cfgs

2020-08-11 23:23:57 +09:00

gluon_xception.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

helpers.py

Initial AGC impl. Still testing.

2021-02-15 23:22:44 -08:00

hrnet.py

Bug in last mod for features_only default_cfg

2020-12-03 12:33:01 -08:00

inception_resnet_v2.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

inception_v3.py

Fix a few small things.

2021-02-09 17:33:43 -08:00

inception_v4.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

mobilenetv3.py

Bug in last mod for features_only default_cfg

2020-12-03 12:33:01 -08:00

nasnet.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

nfnet.py

Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.

2021-02-18 12:28:46 -08:00

pnasnet.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

registry.py

…

regnet.py

Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.

2020-09-24 18:20:36 -07:00

res2net.py

Fix some checkpoint / model str regressions

2020-07-29 19:43:01 -07:00

resnest.py

fix test_model_default_cfgs

2020-08-11 23:23:57 +09:00

resnet.py

Fix some half removed resnet model defs, pooling for ecaresnet269d

2021-02-07 22:09:25 -08:00

resnetv2.py

Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.

2021-02-23 15:54:55 -08:00

rexnet.py

Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.

2021-01-27 22:06:57 -08:00

selecsls.py

fix test_model_default_cfgs

2020-08-11 23:23:57 +09:00

senet.py

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

2020-09-01 16:05:32 -07:00

sknet.py

fix test_model_default_cfgs

2020-08-11 23:23:57 +09:00

tresnet.py

Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast'

2020-09-02 09:11:48 -07:00

vgg.py

Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.

2021-02-09 16:22:52 -08:00

vision_transformer.py

Cleanup experimental vit weight init a bit

2021-03-20 09:44:24 -07:00

vovnet.py

Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.

2020-09-24 18:20:36 -07:00

xception_aligned.py

Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.

2021-02-09 16:22:52 -08:00

xception.py

More uniform treatment of classifiers across all models, reduce code duplication.

2020-08-03 22:18:24 -07:00