| .. |
|
layers
|
All ScaledStdConv and StdConv uses default to using F.layernorm so that they work with PyTorch XLA. eps value tweaking is a WIP.
|
2021-06-07 17:14:19 -07:00 |
|
pruned
|
added efficientnet pruned weights
|
2020-05-03 09:29:45 +03:00 |
|
__init__.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
byoanet.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
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.
|
2021-05-31 13:18:11 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
cspnet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
densenet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
dla.py
|
Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.
|
2021-05-04 21:27:15 -07:00 |
|
dpn.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
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.
|
2021-05-31 13:18:11 -07:00 |
|
efficientnet_blocks.py
|
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
|
2021-05-29 23:41:38 -07:00 |
|
efficientnet_builder.py
|
Able to use other attn layer in EfficientNet now. Create test ECA + GC B0 configs. Make ECA more configurable.
|
2021-05-30 12:47:02 -07:00 |
|
factory.py
|
A few minor fixes and bit more cleanup on the huggingface hub integration.
|
2021-03-17 13:18:52 -07:00 |
|
features.py
|
Fix some attributions, add copyrights to some file docstrings
|
2020-07-27 13:44:56 -07:00 |
|
ghostnet.py
|
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
|
2021-05-29 23:41:38 -07:00 |
|
gluon_resnet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
gluon_xception.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
hardcorenas.py
|
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
|
2021-05-29 23:41:38 -07:00 |
|
helpers.py
|
Fix strict flag change for checkpoint load.
|
2021-05-28 09:54:50 -07:00 |
|
hrnet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
hub.py
|
Change huggingface hub revision delimiter to '@', add hf_hub reference for eca_nfnet_l0 model as an example.
|
2021-03-18 11:38:06 -07:00 |
|
inception_resnet_v2.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
inception_v3.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
inception_v4.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
levit.py
|
Fix #661, move hardswish out of default args for LeViT. Enable native torch support for hardswish, hardsigmoid, mish if present.
|
2021-05-26 15:28:42 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
mobilenetv3.py
|
Bring EfficientNet SE layer in line with others, pull se_ratio outside of blocks. Allows swapping w/ other attn layers.
|
2021-05-29 23:41:38 -07:00 |
|
nasnet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
nfnet.py
|
All ScaledStdConv and StdConv uses default to using F.layernorm so that they work with PyTorch XLA. eps value tweaking is a WIP.
|
2021-06-07 17:14:19 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
pnasnet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
registry.py
|
Filter test models before creation for backward/torchscript tests
|
2021-05-25 10:14:45 -07:00 |
|
regnet.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
res2net.py
|
Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.
|
2021-05-04 21:27:15 -07:00 |
|
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.
|
2021-05-31 13:18:11 -07:00 |
|
resnet.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
resnetv2.py
|
Fix ResNetV2 pretrained classifier issue. Fixes #540
|
2021-04-03 11:18:12 -07:00 |
|
rexnet.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
selecsls.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
senet.py
|
Fix incorrect name of shortcut/identity paths in many residual nets. Inherited from naming in old old torchvision, long fixed there.
|
2021-05-04 21:27:15 -07:00 |
|
sknet.py
|
Remove min channels for SelectiveKernel, divisor should cover cases well enough.
|
2021-05-31 15:38:56 -07:00 |
|
swin_transformer.py
|
Rethink name of patch embed grid info
|
2021-05-06 14:08:20 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
tresnet.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
vgg.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
visformer.py
|
Add Gather-Excite and Global Context attn modules. Refactor existing SE-like attn for consistency and refactor byob/byoanet for less redundancy.
|
2021-05-27 18:03:29 -07:00 |
|
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.
|
2021-05-24 21:13:26 -07:00 |
|
vision_transformer_hybrid.py
|
All ScaledStdConv and StdConv uses default to using F.layernorm so that they work with PyTorch XLA. eps value tweaking is a WIP.
|
2021-06-07 17:14:19 -07:00 |
|
vovnet.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
xception.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
|
xception_aligned.py
|
Support for huggingface hub via create_model and default_cfgs.
|
2021-03-16 22:48:26 -07:00 |
8e4ac3549f