model_maskrcnn: Mask R-CNN Models

In torchvision: Models, Datasets and Transformations for Images

Mask R-CNN Models

Description

Construct Mask R-CNN model variants for instance segmentation task. Mask R-CNN extends Faster R-CNN by adding a mask prediction branch that outputs segmentation masks for each detected object.

Usage

model_maskrcnn_resnet50_fpn(
  pretrained = FALSE,
  progress = TRUE,
  num_classes = 90,
  score_thresh = 0.05,
  nms_thresh = 0.5,
  detections_per_img = 100,
  ...
)

model_maskrcnn_resnet50_fpn_v2(
  pretrained = FALSE,
  progress = TRUE,
  num_classes = 90,
  score_thresh = 0.05,
  nms_thresh = 0.5,
  detections_per_img = 100,
  ...
)

Arguments

pretrained	Logical. If TRUE, loads pretrained weights from local file.
progress	Logical. Show progress bar during download (unused).
num_classes	Number of output classes excluding background (default: 90 for COCO).
score_thresh	Numeric. Minimum score threshold for detections (default: 0.05).
nms_thresh	Numeric. Non-Maximum Suppression (NMS) IoU threshold for removing overlapping boxes (default: 0.5).
detections_per_img	Integer. Maximum number of detections per image (default: 100).
...	Other arguments (unused).

Value

A maskrcnn_model nn_module.

Functions

• model_maskrcnn_resnet50_fpn(): Mask R-CNN with ResNet-50 FPN

• model_maskrcnn_resnet50_fpn_v2(): Mask R-CNN with ResNet-50 FPN V2

Task

Instance segmentation over images with bounding boxes, class labels, and segmentation masks.

Input Format

Input images should be torch_tensors of shape ⁠(batch_size, 3, H, W)⁠ where H and W are typically around 800.

Output Format

Returns a list with:

• features: Feature maps from the backbone

• detections: List containing:

  • boxes: Bounding boxes (N, 4)

  • labels: Class labels (N)

  • scores: Confidence scores (N)

  • masks: Mask probabilities pasted into the image, (N, H, W)

  • mask_probs: Mask probabilities in the box frame, (N, 28, 28)

Available Models

• model_maskrcnn_resnet50_fpn()

• model_maskrcnn_resnet50_fpn_v2()

See Also

Other object_detection_model: model_convnext_detection, model_facenet, model_fasterrcnn, model_lw_detr, model_rfdetr

Examples

## Not run: 
library(magrittr)
# ImageNet normalization constants, see https://pytorch.org/vision/stable/models.html
norm_mean <- c(0.485, 0.456, 0.406)
norm_std  <- c(0.229, 0.224, 0.225)

# Load an image
url <- paste0("https://upload.wikimedia.org/wikipedia/commons/thumb/",
              "e/ea/Morsan_Normande_vache.jpg/120px-Morsan_Normande_vache.jpg")
img <- base_loader(url)

input <- img %>%
  transform_to_tensor() %>%
  transform_resize(c(800, 800)) %>%
  transform_normalize(norm_mean, norm_std)
batch <- input$unsqueeze(1)

# Mask R-CNN ResNet-50 FPN
model <- model_maskrcnn_resnet50_fpn(pretrained = TRUE, detections_per_img = 5)
model$eval()

torch::with_no_grad({pred <- model(batch)$detections[[1]]})

# Visualize boxes
labels <- coco_classes(as.integer(pred$labels))
boxed <- draw_bounding_boxes(image, pred$boxes, labels = labels)
tensor_image_browse(boxed)

## End(Not run)

torchvision documentation built on Oct. 14, 2026, 1:09 a.m.