Mask R-CNN

The Mask R-CNN model is based on the Mask R-CNN paper.


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

Model builders

The following model builders can be used to instantiate a Mask R-CNN model, with or without pre-trained weights. All the model builders internally rely on the torchvision.models.detection.mask_rcnn.MaskRCNN base class. Please refer to the source code for more details about this class.

maskrcnn_resnet50_fpn(*[, weights, ...])

Mask R-CNN model with a ResNet-50-FPN backbone from the Mask R-CNN paper.

maskrcnn_resnet50_fpn_v2(*[, weights, ...])

Improved Mask R-CNN model with a ResNet-50-FPN backbone from the Benchmarking Detection Transfer Learning with Vision Transformers paper.


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