fcn_resnet101

torchvision.models.segmentation.fcn_resnet101(*, weights: Optional[FCN_ResNet101_Weights] = None, progress: bool = True, num_classes: Optional[int] = None, aux_loss: Optional[bool] = None, weights_backbone: Optional[ResNet101_Weights] = ResNet101_Weights.IMAGENET1K_V1, **kwargs: Any) → FCN

Fully-Convolutional Network model with a ResNet-101 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_ResNet101_Weights, optional) – The pretrained weights to use. See FCN_ResNet101_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 (ResNet101_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_ResNet101_Weights(value)

The model builder above accepts the following values as the weights parameter. FCN_ResNet101_Weights.DEFAULT is equivalent to FCN_ResNet101_Weights.COCO_WITH_VOC_LABELS_V1. You can also use strings, e.g. weights='DEFAULT' or weights='COCO_WITH_VOC_LABELS_V1'.

FCN_ResNet101_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_ResNet101_Weights.DEFAULT.

miou (on COCO-val2017-VOC-labels)	63.7
pixel_acc (on COCO-val2017-VOC-labels)	91.9
categories	__background__, aeroplane, bicycle, … (18 omitted)
min_size	height=1, width=1
num_params	54314346
recipe	link
GFLOPS	232.74
File size	207.7 MB

The inference transforms are available at FCN_ResNet101_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].