Ross Wightman ff421e5e09 New PyTorch trained EfficientNet-B2 weights with my RandAugment impl

2019-12-04 11:09:47 -08:00

..

__init__.py

Renamed gen_efficientnet.py -> efficientnet.py

2019-11-28 17:04:35 -08:00

activations.py

Bring EfficientNet and MobileNetV3 up to date with my gen-efficientnet repo

2019-11-28 17:04:35 -08:00

adaptive_avgmax_pool.py

Remove all prints, change most to logging calls, tweak alignment of batch logs, improve setup.py

2019-06-20 17:29:25 -07:00

conv2d_layers.py

Bring EfficientNet and MobileNetV3 up to date with my gen-efficientnet repo

2019-11-28 17:04:35 -08:00

densenet.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

dla.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

dpn.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

efficientnet_blocks.py

Bring EfficientNet and MobileNetV3 up to date with my gen-efficientnet repo

2019-11-28 17:04:35 -08:00

efficientnet_builder.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

efficientnet.py

New PyTorch trained EfficientNet-B2 weights with my RandAugment impl

2019-12-04 11:09:47 -08:00

factory.py

Update EfficientNet comments, MobileNetV3 non-TF create fns, fix factory arg checks, bump PyTorch version req to 1.2

2019-11-28 17:43:00 -08:00

feature_hooks.py

Bring EfficientNet and MobileNetV3 up to date with my gen-efficientnet repo

2019-11-28 17:04:35 -08:00

gluon_resnet.py

ResNet updates:

2019-11-28 17:04:35 -08:00

gluon_xception.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

helpers.py

Add CondConv support for EfficientNet into WIP for GenEfficientNet Feature extraction setup

2019-11-28 17:00:52 -08:00

hrnet.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

inception_resnet_v2.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

inception_v3.py

Update version, results csv files, and move remaining dropbox weights to github

2019-07-25 16:54:44 -07:00

inception_v4.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

median_pool.py

Big re-org, working towards making pip/module as 'timm'

2019-06-19 17:20:51 -07:00

mobilenetv3.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

nasnet.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

pnasnet.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

registry.py

Model updates. Add my best ResNet50 weights top-1=78.47. Add some other torchvision weights.

2019-06-29 15:50:33 -07:00

res2net.py

Fix Mobilenet V3 model name for sotabench. Minor res2net cleanup.

2019-09-05 15:47:56 -07:00

resnet.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

senet.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

test_time_pool.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00

xception.py

Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.

2019-11-29 17:56:36 -08:00