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 022ed001f3 Update DenseNet to latest in Torchvision (torchscript compat, checkpointing, proper init). Start adding ehanced configurability, stem options...		5 years ago
..
layers	Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.	5 years ago
pruned	added efficientnet pruned weights	5 years ago
__init__.py	TResNet models	5 years ago
densenet.py	Update DenseNet to latest in Torchvision (torchscript compat, checkpointing, proper init). Start adding ehanced configurability, stem options...	5 years ago
dla.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
dpn.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
efficientnet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
efficientnet_blocks.py	Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.	5 years ago
efficientnet_builder.py	Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.	5 years ago
factory.py	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.	5 years ago
feature_hooks.py	Bring EfficientNet and MobileNetV3 up to date with my gen-efficientnet repo	5 years ago
gluon_resnet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
gluon_xception.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
helpers.py	Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop	5 years ago
hrnet.py	Replace all None by nn.Identity() in HRNet modules	5 years ago
inception_resnet_v2.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
inception_v3.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
inception_v4.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
mobilenetv3.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
nasnet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
pnasnet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
registry.py	Model updates. Add my best ResNet50 weights top-1=78.47. Add some other torchvision weights.	5 years ago
res2net.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
resnet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
selecsls.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
senet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
sknet.py	Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.	5 years ago
tresnet.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago
xception.py	Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.	5 years ago