torchvision.models.detection.maskrcnn_resnet50_fpn(*, weights: Optional[MaskRCNN_ResNet50_FPN_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, weights_backbone: Optional[ResNet50_Weights] = ResNet50_Weights.IMAGENET1K_V1, trainable_backbone_layers: Optional[int] = None, **kwargs: Any) MaskRCNN[source]

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


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

The input to the model is expected to be a list of tensors, each of shape [C, H, W], one for each image, and should be in 0-1 range. Different images can have different sizes.

The behavior of the model changes depending on if it is in training or evaluation mode.

During training, the model expects both the input tensors and targets (list of dictionary), containing:

  • boxes (FloatTensor[N, 4]): the ground-truth boxes in [x1, y1, x2, y2] format, with 0 <= x1 < x2 <= W and 0 <= y1 < y2 <= H.

  • labels (Int64Tensor[N]): the class label for each ground-truth box

  • masks (UInt8Tensor[N, H, W]): the segmentation binary masks for each instance

The model returns a Dict[Tensor] during training, containing the classification and regression losses for both the RPN and the R-CNN, and the mask loss.

During inference, the model requires only the input tensors, and returns the post-processed predictions as a List[Dict[Tensor]], one for each input image. The fields of the Dict are as follows, where N is the number of detected instances:

  • boxes (FloatTensor[N, 4]): the predicted boxes in [x1, y1, x2, y2] format, with 0 <= x1 < x2 <= W and 0 <= y1 < y2 <= H.

  • labels (Int64Tensor[N]): the predicted labels for each instance

  • scores (Tensor[N]): the scores or each instance

  • masks (UInt8Tensor[N, 1, H, W]): the predicted masks for each instance, in 0-1 range. In order to obtain the final segmentation masks, the soft masks can be thresholded, generally with a value of 0.5 (mask >= 0.5)

For more details on the output and on how to plot the masks, you may refer to Instance segmentation models.

Mask R-CNN is exportable to ONNX for a fixed batch size with inputs images of fixed size.


>>> model = torchvision.models.detection.maskrcnn_resnet50_fpn(weights=MaskRCNN_ResNet50_FPN_Weights.DEFAULT)
>>> model.eval()
>>> x = [torch.rand(3, 300, 400), torch.rand(3, 500, 400)]
>>> predictions = model(x)
>>> # optionally, if you want to export the model to ONNX:
>>> torch.onnx.export(model, x, "mask_rcnn.onnx", opset_version = 11)
  • weights (MaskRCNN_ResNet50_FPN_Weights, optional) – The pretrained weights to use. See MaskRCNN_ResNet50_FPN_Weights below for more details, and possible values. By default, no pre-trained weights are used.

  • progress (bool, optional) – If True, displays a progress bar of the download to stderr. Default is True.

  • num_classes (int, optional) – number of output classes of the model (including the background)

  • weights_backbone (ResNet50_Weights, optional) – The pretrained weights for the backbone.

  • trainable_backbone_layers (int, optional) – number of trainable (not frozen) layers starting from final block. Valid values are between 0 and 5, with 5 meaning all backbone layers are trainable. If None is passed (the default) this value is set to 3.

  • **kwargs – parameters passed to the torchvision.models.detection.mask_rcnn.MaskRCNN base class. Please refer to the source code for more details about this class.

class torchvision.models.detection.MaskRCNN_ResNet50_FPN_Weights(value)[source]

The model builder above accepts the following values as the weights parameter. MaskRCNN_ResNet50_FPN_Weights.DEFAULT is equivalent to MaskRCNN_ResNet50_FPN_Weights.COCO_V1. You can also use strings, e.g. weights='DEFAULT' or weights='COCO_V1'.


These weights were produced by following a similar training recipe as on the paper. Also available as MaskRCNN_ResNet50_FPN_Weights.DEFAULT.

box_map (on COCO-val2017)


mask_map (on COCO-val2017)



__background__, person, bicycle, … (88 omitted)


height=1, width=1







File size

169.8 MB

The inference transforms are available at MaskRCNN_ResNet50_FPN_Weights.COCO_V1.transforms and perform the following preprocessing operations: Accepts PIL.Image, batched (B, C, H, W) and single (C, H, W) image torch.Tensor objects. The images are rescaled to [0.0, 1.0].

Examples using maskrcnn_resnet50_fpn:

Visualization utilities

Visualization utilities


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