torchvision.models.detection.fasterrcnn_resnet50_fpn(*, weights: Optional[FasterRCNN_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) FasterRCNN[source]

Faster R-CNN model with a ResNet-50-FPN backbone from the Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 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 a 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

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

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 detections:

  • 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 detection

  • scores (Tensor[N]): the scores of each detection

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

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


>>> model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights=FasterRCNN_ResNet50_FPN_Weights.DEFAULT)
>>> # For training
>>> images, boxes = torch.rand(4, 3, 600, 1200), torch.rand(4, 11, 4)
>>> boxes[:, :, 2:4] = boxes[:, :, 0:2] + boxes[:, :, 2:4]
>>> labels = torch.randint(1, 91, (4, 11))
>>> images = list(image for image in images)
>>> targets = []
>>> for i in range(len(images)):
>>>     d = {}
>>>     d['boxes'] = boxes[i]
>>>     d['labels'] = labels[i]
>>>     targets.append(d)
>>> output = model(images, targets)
>>> # For inference
>>> 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, "faster_rcnn.onnx", opset_version = 11)
  • weights (FasterRCNN_ResNet50_FPN_Weights, optional) – The pretrained weights to use. See FasterRCNN_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.faster_rcnn.FasterRCNN base class. Please refer to the source code for more details about this class.

class torchvision.models.detection.FasterRCNN_ResNet50_FPN_Weights(value)[source]

The model builder above accepts the following values as the weights parameter. FasterRCNN_ResNet50_FPN_Weights.DEFAULT is equivalent to FasterRCNN_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 FasterRCNN_ResNet50_FPN_Weights.DEFAULT.

box_map (on COCO-val2017)



__background__, person, bicycle, … (88 omitted)


height=1, width=1







File size

159.7 MB

The inference transforms are available at FasterRCNN_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 fasterrcnn_resnet50_fpn:

Repurposing masks into bounding boxes

Repurposing masks into bounding boxes

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