| .. |
|
layers
|
Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.
|
2020-05-04 12:14:43 -07:00 |
|
pruned
|
added efficientnet pruned weights
|
2020-05-03 09:29:45 +03:00 |
|
__init__.py
|
TResNet models
|
2020-04-12 18:44:12 +03:00 |
|
densenet.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
dla.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
dpn.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
efficientnet.py
|
added efficientnet pruned weights
|
2020-05-03 09:29:45 +03:00 |
|
efficientnet_blocks.py
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
2020-04-09 01:41:54 -07:00 |
|
efficientnet_builder.py
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
2020-04-09 01:41:54 -07:00 |
|
factory.py
|
Unify drop connect vs drop path under 'drop path' name, switch all EfficientNet/MobilenetV3 refs to 'drop_path'. Update factory to handle new drop args.
|
2020-02-18 14:00:26 -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
|
Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
|
2020-02-10 11:55:03 -08:00 |
|
gluon_xception.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
helpers.py
|
Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop
|
2020-05-01 17:00:21 -07:00 |
|
hrnet.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
inception_resnet_v2.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -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
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
mobilenetv3.py
|
Merge changes in feature extraction interface to MobileNetV3
|
2020-04-13 02:02:14 +03:00 |
|
nasnet.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
pnasnet.py
|
Fix model create fn not passing num_classes through. Fix #135
|
2020-05-01 18:37:03 -07:00 |
|
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 model create fn not passing num_classes through. Fix #135
|
2020-05-01 18:37:03 -07:00 |
|
resnet.py
|
Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop
|
2020-05-01 17:00:21 -07:00 |
|
selecsls.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
senet.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
|
sknet.py
|
Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.
|
2020-05-04 12:14:43 -07:00 |
|
tresnet.py
|
Small TResNet simplification, just use SelectAdaptivePool, don't notice any perf difference
|
2020-04-27 17:50:19 -07:00 |
|
xception.py
|
Big move, layer modules and fn to timm/models/layers
|
2020-02-09 13:13:08 -08:00 |
8d8677e03b