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.
pytorch-image-models/timm/models
Ross Wightman e8e2d9cabf
Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args.
4 years ago
..
layers More models in sotabench, more control over sotabench run, dataset filename extraction consistency 4 years ago
pruned
__init__.py
cspnet.py
densenet.py
dla.py
dpn.py
efficientnet.py Add EfficientNet-EdgeTPU-M (efficientnet_em) model trained natively in PyTorch. More sotabench fiddling. 4 years ago
efficientnet_blocks.py
efficientnet_builder.py
factory.py Add global_pool (--gp) arg changes to allow passing 'fast' easily for train/validate to avoid channels_last issue with AdaptiveAvgPool 4 years ago
features.py
gluon_resnet.py
gluon_xception.py
helpers.py Cleanup Apex vs native AMP scaler state save/load. Cleanup CheckpointSaver a bit. 4 years ago
hrnet.py
inception_resnet_v2.py
inception_v3.py
inception_v4.py
mobilenetv3.py
nasnet.py
pnasnet.py
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
resnet.py Add ResNet weights. 80.5 (top-1) ResNet-50-D, 77.1 ResNet-34-D, 72.7 ResNet-18-D. 4 years ago
rexnet.py Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args. 4 years ago
selecsls.py
senet.py
sknet.py
tresnet.py
vovnet.py Add DropPath (stochastic depth) to ReXNet and VoVNet. RegNet DropPath impl tweak and dedupe se args. 4 years ago
xception.py
xception_aligned.py