pytorch-image-models

History

Ross Wightman 01cb46a9a5 Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.		3 years ago
..
layers	Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.	3 years ago
pruned	…
__init__.py	wip xcit	3 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 efficientnetv2_rw_t defs w/ weights, and gc variant, as well as gcresnet26ts for experiments. Version 0.4.13	3 years ago
cait.py	Refactoring, cleanup, improved test coverage.	3 years ago
coat.py	Refactoring, cleanup, improved test coverage.	3 years ago
convit.py	Merge branch 'master' into cleanup_xla_model_fixes	3 years ago
cspnet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
densenet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
dla.py	Refactoring, cleanup, improved test coverage.	3 years ago
dpn.py	Refactoring, cleanup, improved test coverage.	3 years ago
efficientnet.py	Add gc_efficientnetv2_rw_t weights (global context instead of SE attn). Add TF XL weights even though the fine-tuned ones don't validate that well. Change default arg for GlobalContext to use scal (mul) mode.	3 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	A few minor fixes and bit more cleanup on the huggingface hub integration.	4 years ago
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	3 years ago
gluon_resnet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
gluon_xception.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
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.	3 years ago
hrnet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
hub.py	Change huggingface hub revision delimiter to '@', add hf_hub reference for eca_nfnet_l0 model as an example.	4 years ago
inception_resnet_v2.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
inception_v3.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
inception_v4.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
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	3 years ago
mlp_mixer.py	Add gMLP-S weights, 79.6 top-1	3 years ago
mobilenetv3.py	Refactoring, cleanup, improved test coverage.	3 years ago
nasnet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
nest.py	Use bicubic interpolation in resize_pos_embed()	3 years ago
nfnet.py	Refactoring, cleanup, improved test coverage.	3 years ago
pit.py	Refactoring, cleanup, improved test coverage.	3 years ago
pnasnet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
registry.py	Refactoring, cleanup, improved test coverage.	3 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	Refactoring, cleanup, improved test coverage.	3 years ago
resnetv2.py	Fix features for resnetv2_50t	3 years ago
rexnet.py	Post merge cleanup	3 years ago
selecsls.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
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.	3 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.	3 years ago
vgg.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
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	3 years ago
vision_transformer.py	Use bicubic interpolation in resize_pos_embed()	3 years ago
vision_transformer_hybrid.py	AugReg release	3 years ago
vovnet.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
xception.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
xception_aligned.py	Support for huggingface hub via create_model and default_cfgs.	4 years ago
xcit.py	Allow act_layer switch for xcit, fix in_chans for some variants	3 years ago