You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Ross Wightman 55f7dfa9ea Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing		4 years ago
..
layers	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
pruned	…
__init__.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.	4 years ago
cspnet.py	Add CSPResNet50 weights, 79.6 top-1 at 256x256	4 years ago
densenet.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
dla.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
dpn.py	Remove some old __future__ imports	4 years ago
efficientnet.py	Bug in last mod for features_only default_cfg	4 years ago
efficientnet_blocks.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	4 years ago
efficientnet_builder.py	…
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.	4 years ago
features.py	…
gluon_resnet.py	fix test_model_default_cfgs	4 years ago
gluon_xception.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
helpers.py	More dataset work including factories and a tensorflow datasets (TFDS) wrapper	4 years ago
hrnet.py	Bug in last mod for features_only default_cfg	4 years ago
inception_resnet_v2.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
inception_v3.py	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
inception_v4.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
mobilenetv3.py	Bug in last mod for features_only default_cfg	4 years ago
nasnet.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.	4 years ago
pnasnet.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
registry.py	…
regnet.py	Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.	4 years ago
res2net.py	…
resnest.py	fix test_model_default_cfgs	4 years ago
resnet.py	Add 320x320 model default cfgs for 101D and 152D ResNets. Add SEResNet-152D weights and 320x320 cfg.	4 years ago
resnetv2.py	Finishing adding stochastic depth support to BiT ResNetV2 models	4 years ago
rexnet.py	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	4 years ago
selecsls.py	fix test_model_default_cfgs	4 years ago
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	4 years ago
sknet.py	fix test_model_default_cfgs	4 years ago
tresnet.py	Add 'fast' global pool option, remove redundant SEModule from tresnet, normal one is now 'fast'	4 years ago
vision_transformer.py	Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing	4 years ago
vovnet.py	Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.	4 years ago
xception.py	More uniform treatment of classifiers across all models, reduce code duplication.	4 years ago
xception_aligned.py	Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers.	4 years ago