composer.models.deeplabv3.deeplabv3#
composer.models.deeplabv3.deeplabv3
Functions
Helper function to build a torchvision DeepLabV3 model with a 3x3 convolution layer and dropout removed. |
|
Drop-in replacement for |
Classes
|
torchvision.models.segmentation.deeplabv3.ASPP |
DeepLabV3 model extending the |
|
The minimal interface needed to use a model with |
|
Torchmetric cross entropy loss implementation. |
|
|
Implements DeepLabV3 model from "Rethinking Atrous Convolution for Semantic Image Segmentation". |
An enumeration. |
|
Torchmetric mean Intersection-over-Union (mIoU) implementation. |
|
|
MetricCollection class can be used to chain metrics that have the same call pattern into one single class. |
Attributes
Any
BatchPair
List
- class composer.models.deeplabv3.deeplabv3.ComposerDeepLabV3(num_classes, backbone_arch='resnet101', is_backbone_pretrained=True, sync_bn=True, initializers=[])[source]#
Bases:
composer.models.base.ComposerModel
DeepLabV3 model extending the
ComposerClassifier
.See arxiv.org/abs/1706.05587 for more details on the DeepLabV3 architecture.
- Parameters
num_classes (int) โ the number of classes in the segmentation task.
backbone_arch (str) โ the backbone architecture to use, either โresnet50โ, โresnet101โ. Default is โresnet101โ.
is_backbone_pretrained (bool) โ if true (default), use pre-trained weights for backbone.
sync_bn (bool) โ if true (default), use SyncBatchNorm to sync batch norm statistics across GPUs.
- composer.models.deeplabv3.deeplabv3.deeplabv3_builder(num_classes, backbone_arch='resnet101', is_backbone_pretrained=True, sync_bn=True, initializers=[])[source]#
Helper function to build a torchvision DeepLabV3 model with a 3x3 convolution layer and dropout removed.
- Parameters
num_classes (int) โ number of classes in the segmentation task.
backbone_arch (str) โ the architecture to use for the backbone. Must be either [โresnet50โ, โresnet101โ]. Default is โresnet101โ.
is_backbone_pretrained (bool) โ if true (default), use pretrained weights for the backbone.
sync_bn (bool) โ if true (default), replace all BatchNorm layers with SyncBatchNorm layers.