The DeepLabV3 model is based on the Rethinking Atrous Convolution for Semantic Image Segmentation paper.


The segmentation module is in Beta stage, and backward compatibility is not guaranteed.

Model builders

The following model builders can be used to instantiate a DeepLabV3 model with different backbones, with or without pre-trained weights. All the model builders internally rely on the torchvision.models.segmentation.deeplabv3.DeepLabV3 base class. Please refer to the source code for more details about this class.

deeplabv3_mobilenet_v3_large(*[, weights, ...])

Constructs a DeepLabV3 model with a MobileNetV3-Large backbone.

deeplabv3_resnet50(*[, weights, progress, ...])

Constructs a DeepLabV3 model with a ResNet-50 backbone.

deeplabv3_resnet101(*[, weights, progress, ...])

Constructs a DeepLabV3 model with a ResNet-101 backbone.


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources