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 5fcddb96a8 Merge branch 'master' into cait		3 years ago
..
layers	Improved (hopefully) init for SA/SA-like layers used in ByoaNets	3 years ago
pruned	…
__init__.py	Merge branch 'master' into cait	3 years ago
byoanet.py	Improved (hopefully) init for SA/SA-like layers used in ByoaNets	3 years ago
byobnet.py	Update ByoaNet comments. Fix first Steam feat chs for ByobNet.	4 years ago
cait.py	Finish CaiT cleanup	3 years ago
coat.py	Fix coat first conv ident	3 years ago
cspnet.py	…
densenet.py	…
dla.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
dpn.py	…
efficientnet.py	Add updated EfficientNet-V2S weights, 83.8 @ 384x384 test. Add PyTorch trained EfficientNet-B4 weights, 83.4 @ 384x384 test. Tweak non TF EfficientNet B1-B4 train/test res scaling.	3 years ago
efficientnet_blocks.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
efficientnet_builder.py	…
factory.py	…
features.py	…
ghostnet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	…
helpers.py	…
hrnet.py	…
hub.py	…
inception_resnet_v2.py	…
inception_v3.py	…
inception_v4.py	…
mlp_mixer.py	Add official pretrained weights to MLP-Mixer, complete model cfgs.	3 years ago
mobilenetv3.py	A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.	3 years ago
nasnet.py	…
nfnet.py	Add prelim efficientnet_v2s weights from 224x224 train, eval 83.3 @ 288. Add eca_nfnet_l1 weights, train at 256, eval 84 @ 320.	4 years ago
pit.py	Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer	4 years ago
pnasnet.py	…
registry.py	Add default_cfg options for min_input_size / fixed_input_size, queries in model registry, and use for testing self-attn models	4 years ago
regnet.py	…
res2net.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
resnest.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
resnet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
resnetv2.py	…
rexnet.py	…
selecsls.py	…
senet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
sknet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
swin_transformer.py	Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer	4 years ago
tnt.py	Add Swin Transformer models from https://github.com/microsoft/Swin-Transformer	4 years ago
tresnet.py	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	3 years ago
vgg.py	…
vision_transformer.py	A few miil weights naming tweaks to improve compat with model registry and filtering wildcards.	3 years ago
vision_transformer_hybrid.py	…
vovnet.py	…
xception.py	…
xception_aligned.py	…