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 b1c2e3eb92 Match rel_pos_indices attr rename in conv branch		3 years ago
..
layers	Match rel_pos_indices attr rename in conv branch	3 years ago
pruned	…
__init__.py	Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now	3 years ago
beit.py	Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now	3 years ago
byoanet.py	Add relative pos embed option to LambdaLayer, fix last transpose/reshape.	3 years ago
byobnet.py	Make 'regnetz' model experiments closer to actual RegNetZ, bottleneck expansion, expand from in_chs, no shortcut on stride 2, tweak model sizes	3 years ago
cait.py	Refactoring, cleanup, improved test coverage.	4 years ago
coat.py	Refactoring, cleanup, improved test coverage.	4 years ago
convit.py	Merge branch 'master' into cleanup_xla_model_fixes	4 years ago
crossvit.py	A few more crossvit tweaks, fix training w/ no_weight_decay names, add crop option for scaling, adjust default crop_pct for large img size to 1.0 for better results	3 years ago
cspnet.py	…
densenet.py	…
dla.py	Refactoring, cleanup, improved test coverage.	4 years ago
dpn.py	Refactoring, cleanup, improved test coverage.	4 years ago
efficientnet.py	make it possible to provide norm_layer via create_model	3 years ago
efficientnet_blocks.py	Remove dead code line from efficientnet	3 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	Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713	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	Refactoring, cleanup, improved test coverage.	4 years ago
hrnet.py	…
hub.py	…
inception_resnet_v2.py	…
inception_v3.py	…
inception_v4.py	…
levit.py	Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713	4 years ago
mlp_mixer.py	Add gMLP-S weights, 79.6 top-1	4 years ago
mobilenetv3.py	Refactoring, cleanup, improved test coverage.	4 years ago
nasnet.py	…
nest.py	Use bicubic interpolation in resize_pos_embed()	3 years ago
nfnet.py	Refactoring, cleanup, improved test coverage.	4 years ago
pit.py	Refactoring, cleanup, improved test coverage.	4 years ago
pnasnet.py	…
registry.py	Refactoring, cleanup, improved test coverage.	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	Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.	4 years ago
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 baseline resnet26t @ 256x256 weights. Add 33ts variant of halonet with at least one halo in stage 2,3,4	3 years ago
resnetv2.py	ResNetV2 seems to work best without zero_init residual	3 years ago
rexnet.py	Post merge cleanup	4 years ago
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.	4 years ago
sknet.py	Remove min channels for SelectiveKernel, divisor should cover cases well enough.	4 years ago
swin_transformer.py	Refactoring, cleanup, improved test coverage.	4 years ago
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	Refactoring, cleanup, improved test coverage.	4 years ago
vgg.py	…
visformer.py	Fix a few issues loading pretrained vit/bit npz weights w/ num_classes=0 __init__ arg. Missed a few other small classifier handling detail on Mlp, GhostNet, Levit. Should fix #713	4 years ago
vision_transformer.py	Fix silly typo	3 years ago
vision_transformer_hybrid.py	AugReg release	4 years ago
vovnet.py	…
xception.py	…
xception_aligned.py	…
xcit.py	Allow act_layer switch for xcit, fix in_chans for some variants	3 years ago