thelper.nn.segmentation package¶
Neural network and model package for segemnation.
This package contains classes that define blocks and modules used in various neural network for segmentation
Submodules¶
thelper.nn.segmentation.base module¶
-
class
thelper.nn.segmentation.base.
SegmModelBase
(task, pretrained=False)[source]¶ Bases:
thelper.nn.utils.Module
Base wrapper class for specialized segmentation models.
-
in_channels
= None¶
-
model_cls
= None¶
-
thelper.nn.segmentation.deeplabv3 module¶
-
class
thelper.nn.segmentation.deeplabv3.
DeepLabV3ResNet101
(task, pretrained=False)[source]¶ Bases:
thelper.nn.segmentation.base.SegmModelBase
This class is a thin wrapper for
torchvision.models.segmentation.deeplabv3_resnet101()
(torchvision > 0.6
).Note
Contributed by Mario Beaulieu <mario.beaulieu@crim.ca>.
See also
Liang-Chieh et al., Rethinking Atrous Convolution for Semantic Image Segmentation [arXiv], 2017.
-
class
thelper.nn.segmentation.deeplabv3.
DeepLabV3ResNet50
(task, pretrained=False)[source]¶ Bases:
thelper.nn.segmentation.base.SegmModelBase
This class is a thin wrapper for
torchvision.models.segmentation.deeplabv3_resnet101()
(torchvision > 0.6
).Note
Contributed by Mario Beaulieu <mario.beaulieu@crim.ca>.
See also
Liang-Chieh et al., Rethinking Atrous Convolution for Semantic Image Segmentation [arXiv], 2017.
thelper.nn.segmentation.fcn module¶
-
class
thelper.nn.segmentation.fcn.
FCNResNet101
(task, pretrained=False)[source]¶ Bases:
thelper.nn.segmentation.base.SegmModelBase
This class is a thin wrapper for
torchvision.models.segmentation.fcn_resnet50()
(torchvision > 0.6
).Note
Contributed by Mario Beaulieu <mario.beaulieu@crim.ca>.
See also
Liang-Chieh et al., Rethinking Atrous Convolution for Semantic Image Segmentation [arXiv], 2017.
-
class
thelper.nn.segmentation.fcn.
FCNResNet50
(task, pretrained=False)[source]¶ Bases:
thelper.nn.segmentation.base.SegmModelBase
This class is a thin wrapper for
torchvision.models.segmentation.fcn_resnet50()
(torchvision > 0.6
).Note
Contributed by Mario Beaulieu <mario.beaulieu@crim.ca>.
See also
Liang-Chieh et al., Rethinking Atrous Convolution for Semantic Image Segmentation [arXiv], 2017.