Ross Wightman e2b8d44ff0 Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs ...

* align interfaces of halo, bottleneck attn and lambda layer
* add qk_ratio to all of above, control q/k dim relative to output dim
* add experimental haloregnetz, and trionet (lambda + halo + bottle) models

2021-10-06 16:32:48 -07:00

..

layers

Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs

2021-10-06 16:32:48 -07:00

pruned

…

__init__.py

Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now

2021-09-13 16:38:23 -07:00

beit.py

Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now

2021-09-13 16:38:23 -07:00

byoanet.py

Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs

2021-10-06 16:32:48 -07:00

byobnet.py

Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs

2021-10-06 16:32:48 -07:00

cait.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

coat.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

convit.py

Merge branch 'master' into cleanup_xla_model_fixes

2021-06-12 23:19:25 -07:00

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

2021-09-13 14:17:34 -07:00

cspnet.py

…

densenet.py

…

dla.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

dpn.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

efficientnet_blocks.py

Remove dead code line from efficientnet

2021-09-30 21:54:42 -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

efficientnet.py

make it possible to provide norm_layer via create_model

2021-09-21 10:19:04 +01:00

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

2021-06-22 23:16:05 -07:00

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.

2021-05-29 23:41:38 -07:00

helpers.py

support bits checkpoints in avg/load

2021-10-03 17:31:22 -07:00

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

2021-06-22 23:16:05 -07:00

mlp_mixer.py

Add gMLP-S weights, 79.6 top-1

2021-06-23 10:40:30 -07:00

mobilenetv3.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

nasnet.py

…

nest.py

Use bicubic interpolation in resize_pos_embed()

2021-07-12 10:38:31 -07:00

nfnet.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

pit.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

pnasnet.py

…

registry.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

regnet.py

…

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.

2021-05-31 13:18:11 -07:00

resnet.py

Change crop ratio on correct resnet50 variant.

2021-10-04 22:31:08 -07:00

resnetv2.py

Clean a1/a2/3 rsb _0 checkpoints properly, fix v2 loading.

2021-10-04 16:46:00 -07:00

rexnet.py

Post merge cleanup

2021-06-07 14:38:30 -07:00

selecsls.py

…

senet.py

…

sknet.py

Remove min channels for SelectiveKernel, divisor should cover cases well enough.

2021-05-31 15:38:56 -07:00

swin_transformer.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

tnt.py

…

tresnet.py

…

twins.py

Refactoring, cleanup, improved test coverage.

2021-06-12 16:40:02 -07:00

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

2021-06-22 23:16:05 -07:00

vision_transformer_hybrid.py

AugReg release

2021-06-20 17:46:06 -07:00

vision_transformer.py

Fix silly typo

2021-08-27 09:22:20 -07:00

vovnet.py

…

xception_aligned.py

…

xception.py

…

xcit.py

Allow act_layer switch for xcit, fix in_chans for some variants

2021-07-12 13:27:29 -07:00