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 b401952caf
Add newly added vision transformer large/base 224x224 weights ported from JAX official repo
4 years ago
..
layers Support native silu activation (aka swish). An optimized ver is available in PyTorch 1.7. 4 years ago
pruned
__init__.py Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers. 4 years ago
cspnet.py
densenet.py
dla.py
dpn.py
efficientnet.py
efficientnet_blocks.py
efficientnet_builder.py
factory.py
features.py
gluon_resnet.py
gluon_xception.py
helpers.py Fix regression for pretrained classifier loading when using entrypt functions directly 4 years ago
hrnet.py Fix regression for pretrained classifier loading when using entrypt functions directly 4 years ago
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
rexnet.py Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers. 4 years ago
selecsls.py
senet.py
sknet.py
tresnet.py
vision_transformer.py Add newly added vision transformer large/base 224x224 weights ported from JAX official repo 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
xception_aligned.py Initial Vision Transformer impl w/ patch and hybrid variants. Refactor tuple helpers. 4 years ago