torchvision.models.detection.keypointrcnn_resnet50_fpn(*, weights: Optional[KeypointRCNN_ResNet50_FPN_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, num_keypoints: Optional[int] = None, weights_backbone: Optional[ResNet50_Weights] = ResNet50_Weights.IMAGENET1K_V1, trainable_backbone_layers: Optional[int] = None, **kwargs: Any) KeypointRCNN[source]

Constructs a Keypoint R-CNN model with a ResNet-50-FPN backbone.


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

Reference: Mask R-CNN.

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

  • keypoints (FloatTensor[N, K, 3]): the K keypoints location for each of the N instances, in the format [x, y, visibility], where visibility=0 means that the keypoint is not visible.

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

  • keypoints (FloatTensor[N, K, 3]): the locations of the predicted keypoints, in [x, y, v] format.

For more details on the output, you may refer to Instance segmentation models.

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


>>> model = torchvision.models.detection.keypointrcnn_resnet50_fpn(weights=KeypointRCNN_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, "keypoint_rcnn.onnx", opset_version = 11)
  • weights (KeypointRCNN_ResNet50_FPN_Weights, optional) – The pretrained weights to use. See KeypointRCNN_ResNet50_FPN_Weights below for more details, and possible values. By default, no pre-trained weights are used.

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

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

  • num_keypoints (int, optional) – number of keypoints

  • 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.

class torchvision.models.detection.KeypointRCNN_ResNet50_FPN_Weights(value)[source]

An enumeration.

Examples using KeypointRCNN_ResNet50_FPN_Weights:

Visualization utilities

Visualization utilities

Examples using keypointrcnn_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