Shortcuts

fcn_resnet50

torchvision.models.segmentation.fcn_resnet50(*, weights: Optional[FCN_ResNet50_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, aux_loss: Optional[bool] = None, weights_backbone: Optional[ResNet50_Weights] = ResNet50_Weights.IMAGENET1K_V1, **kwargs: Any) FCN[source]

Fully-Convolutional Network model with a ResNet-50 backbone from the Fully Convolutional Networks for Semantic Segmentation paper.

Warning

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

Parameters:
  • weights (FCN_ResNet50_Weights, optional) – The pretrained weights to use. See FCN_ResNet50_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).

  • aux_loss (bool, optional) – If True, it uses an auxiliary loss.

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

  • **kwargs – parameters passed to the torchvision.models.segmentation.fcn.FCN base class. Please refer to the source code for more details about this class.

class torchvision.models.segmentation.FCN_ResNet50_Weights(value)[source]

The model builder above accepts the following values as the weights parameter. FCN_ResNet50_Weights.DEFAULT is equivalent to FCN_ResNet50_Weights.COCO_WITH_VOC_LABELS_V1. You can also use strings, e.g. weights='DEFAULT' or weights='COCO_WITH_VOC_LABELS_V1'.

FCN_ResNet50_Weights.COCO_WITH_VOC_LABELS_V1:

These weights were trained on a subset of COCO, using only the 20 categories that are present in the Pascal VOC dataset. Also available as FCN_ResNet50_Weights.DEFAULT.

miou (on COCO-val2017-VOC-labels)

60.5

pixel_acc (on COCO-val2017-VOC-labels)

91.4

categories

__background__, aeroplane, bicycle, … (18 omitted)

min_size

height=1, width=1

num_params

35322218

recipe

link

GFLOPS

152.72

File size

135.0 MB

The inference transforms are available at FCN_ResNet50_Weights.COCO_WITH_VOC_LABELS_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 resized to resize_size=[520] using interpolation=InterpolationMode.BILINEAR. Finally the values are first rescaled to [0.0, 1.0] and then normalized using mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].

Examples using fcn_resnet50:

Visualization utilities

Visualization utilities

Visualization utilities

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources