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 36989cfae4 Factor out readme generation in hub helper, add more readme fields		2 years ago
..
_pruned	…
layers	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
__init__.py	…
_builder.py	Change order of checkpoitn filtering fn application in builder, try dict, model variant first	2 years ago
_efficientnet_blocks.py	…
_efficientnet_builder.py	…
_factory.py	…
_features.py	…
_features_fx.py	…
_helpers.py	…
_hub.py	Factor out readme generation in hub helper, add more readme fields	2 years ago
_manipulate.py	…
_pretrained.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
_prune.py	…
_registry.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
beit.py	Switch BEiT to HF hub weights	2 years ago
byoanet.py	…
byobnet.py	Pass through --model-kwargs (and --opt-kwargs for train) from command line through to model __init__. Update some models to improve arg overlay. Cleanup along the way.	2 years ago
cait.py	…
coat.py	…
convit.py	…
convmixer.py	…
convnext.py	Add convnext_tiny and convnext_small 384x384 fine-tunes of in12k weights, fix pool size for laion CLIP convnext weights	2 years ago
crossvit.py	…
cspnet.py	Update ClassifierHead module, add reset() method, update in_chs -> in_features for consistency	2 years ago
deit.py	…
densenet.py	More kwarg handling tweaks, maxvit_base_rw def added	2 years ago
dla.py	…
dpn.py	More kwarg handling tweaks, maxvit_base_rw def added	2 years ago
edgenext.py	…
efficientformer.py	…
efficientnet.py	…
factory.py	…
features.py	…
fx_features.py	…
gcvit.py	…
ghostnet.py	…
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	…
helpers.py	…
hrnet.py	…
hub.py	…
inception_resnet_v2.py	…
inception_v3.py	…
inception_v4.py	…
levit.py	…
maxxvit.py	Push all MaxxViT weights to HF hub, cleanup impl, add feature map extraction support and prompote to 'std' architecture. Fix norm head for proper embedding / feat map output. Add new in12k + ft 1k weights.	2 years ago
mlp_mixer.py	…
mobilenetv3.py	…
mobilevit.py	More kwarg handling tweaks, maxvit_base_rw def added	2 years ago
mvitv2.py	…
nasnet.py	…
nest.py	…
nfnet.py	Pass through --model-kwargs (and --opt-kwargs for train) from command line through to model __init__. Update some models to improve arg overlay. Cleanup along the way.	2 years ago
pit.py	…
pnasnet.py	…
poolformer.py	…
pvt_v2.py	…
registry.py	…
regnet.py	Update ClassifierHead module, add reset() method, update in_chs -> in_features for consistency	2 years ago
res2net.py	Improving kwarg merging in more models	2 years ago
resnest.py	Improving kwarg merging in more models	2 years ago
resnet.py	More kwarg handling tweaks, maxvit_base_rw def added	2 years ago
resnetv2.py	More kwarg handling tweaks, maxvit_base_rw def added	2 years ago
rexnet.py	…
selecsls.py	…
senet.py	…
sequencer.py	…
sknet.py	Fix ResNet based models to work w/ norm layers w/o affine params. Reformat long arg lists into vertical form.	2 years ago
swin_transformer.py	…
swin_transformer_v2.py	…
swin_transformer_v2_cr.py	…
tnt.py	…
tresnet.py	…
twins.py	…
vgg.py	…
visformer.py	…
vision_transformer.py	Re-order vit pretrained entries for more sensible default weights (no .tag specified)	2 years ago
vision_transformer_hybrid.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
vision_transformer_relpos.py	Add FlexiViT models and weights, refactoring, push more weights	2 years ago
volo.py	…
vovnet.py	Pass through --model-kwargs (and --opt-kwargs for train) from command line through to model __init__. Update some models to improve arg overlay. Cleanup along the way.	2 years ago
xception.py	…
xception_aligned.py	Update ClassifierHead module, add reset() method, update in_chs -> in_features for consistency	2 years ago
xcit.py	…