.. |
layers
|
Add custom grad tests, fix cut & paste error with hard_mish ME, add a few more pytorch act fns to factory
|
5 years ago |
pruned
|
added efficientnet pruned weights
|
5 years ago |
__init__.py
|
Monster commit, activation refactor, VoVNet, norm_act improvements, more
|
5 years ago |
densenet.py
|
Remove pointless densenet configs, add an iabn version of 264 as it makes more sense to try someday...
|
5 years ago |
dla.py
|
Merge branch 'master' into densenet_update_and_more
|
5 years ago |
dpn.py
|
Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit.
|
5 years ago |
efficientnet.py
|
Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size)
|
5 years ago |
efficientnet_blocks.py
|
Fix an an untested change, remove a debug print
|
5 years ago |
efficientnet_builder.py
|
Monster commit, activation refactor, VoVNet, norm_act improvements, more
|
5 years ago |
factory.py
|
Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit.
|
5 years ago |
feature_hooks.py
|
Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size)
|
5 years ago |
gluon_resnet.py
|
Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.
|
5 years ago |
gluon_xception.py
|
Merge branch 'master' into densenet_update_and_more
|
5 years ago |
helpers.py
|
Final blurpool2d cleanup and add resnetblur50 weights, match tresnet Downsample arg order to BlurPool2d for interop
|
5 years ago |
hrnet.py
|
Add backward and default_cfg tests and fix a few issues found. Fix #153
|
5 years ago |
inception_resnet_v2.py
|
Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit.
|
5 years ago |
inception_v3.py
|
Merge branch 'master' into densenet_update_and_more
|
5 years ago |
inception_v4.py
|
Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.
|
5 years ago |
mobilenetv3.py
|
Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size)
|
5 years ago |
nasnet.py
|
Merge branch 'master' into densenet_update_and_more
|
5 years ago |
pnasnet.py
|
Monster commit, activation refactor, VoVNet, norm_act improvements, more
|
5 years ago |
registry.py
|
Exclude EfficientNet-L2 models from test
|
5 years ago |
regnet.py
|
Update regnet cfg keys to match model names so registry works properly
|
5 years ago |
res2net.py
|
Fix two regressions
|
5 years ago |
resnest.py
|
Fix #173, lr cycle default 0 vs 1. Fix #177, mirror resnest weights for future stability.
|
5 years ago |
resnet.py
|
Monster commit, activation refactor, VoVNet, norm_act improvements, more
|
5 years ago |
selecsls.py
|
Monster commit, activation refactor, VoVNet, norm_act improvements, more
|
5 years ago |
senet.py
|
Replace all None by nn.Identity() in all models reset_classifier when False-values num_classes is given.
|
5 years ago |
sknet.py
|
Fix #139. Broken SKResNets after BlurPool addition, as a plus, SKResNets support AA now too.
|
5 years ago |
tresnet.py
|
Monster commit, activation refactor, VoVNet, norm_act improvements, more
|
5 years ago |
vovnet.py
|
Add ESE-VoVNet-19-DW weights
|
5 years ago |
xception.py
|
Merge branch 'master' into densenet_update_and_more
|
5 years ago |