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 bda8ab015a Remove min channels for SelectiveKernel, divisor should cover cases well enough.		4 years ago
..
layers	Remove min channels for SelectiveKernel, divisor should cover cases well enough.	4 years ago
pruned	…
__init__.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
byoanet.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
byobnet.py	Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.	4 years ago
cait.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
coat.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
convit.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
cspnet.py	…
densenet.py	…
dla.py	…
dpn.py	…
efficientnet.py	Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.	4 years ago
efficientnet_blocks.py	Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.	4 years ago
efficientnet_builder.py	Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.	4 years ago
factory.py	…
features.py	…
ghostnet.py	Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.	4 years ago
gluon_resnet.py	…
gluon_xception.py	…
hardcorenas.py	Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.	4 years ago
helpers.py	Fix strict flag change for checkpoint load.	4 years ago
hrnet.py	…
hub.py	…
inception_resnet_v2.py	…
inception_v3.py	…
inception_v4.py	…
levit.py	Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.	4 years ago
mlp_mixer.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
mobilenetv3.py	Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.	4 years ago
nasnet.py	…
nfnet.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
pit.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
pnasnet.py	…
registry.py	Filter test models before creation for backward/torchscript tests	4 years ago
regnet.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
res2net.py	…
resnest.py	Add non-local and BAT attention. Merge attn and self-attn factories into one. Add attention references to README. Add mlp 'mode' to ECA.	4 years ago
resnet.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
resnetv2.py	…
rexnet.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
selecsls.py	…
senet.py	…
sknet.py	Remove min channels for SelectiveKernel, divisor should cover cases well enough.	4 years ago
swin_transformer.py	…
tnt.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
tresnet.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
twins.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
vgg.py	…
visformer.py	Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.	4 years ago
vision_transformer.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
vision_transformer_hybrid.py	Expand scope of testing for non-std vision transformer / mlp models. Some related cleanup and create fn cleanup for all vision transformer and mlp models. More CoaT weights.	4 years ago
vovnet.py	…
xception.py	…
xception_aligned.py	…