model_fasterrcnn: Faster R-CNN Models

In torchvision: Models, Datasets and Transformations for Images

Faster R-CNN Models

Description

Construct Faster R-CNN model variants for object detection tasks.

Usage

model_fasterrcnn_resnet50_fpn(
  pretrained = FALSE,
  progress = TRUE,
  num_classes = 91,
  ...
)

model_fasterrcnn_resnet50_fpn_v2(
  pretrained = FALSE,
  progress = TRUE,
  num_classes = 91,
  ...
)

model_fasterrcnn_mobilenet_v3_large_fpn(
  pretrained = FALSE,
  progress = TRUE,
  num_classes = 91,
  ...
)

model_fasterrcnn_mobilenet_v3_large_320_fpn(
  pretrained = FALSE,
  progress = TRUE,
  num_classes = 91,
  ...
)

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 (default: 91 for COCO).
...	Other arguments (unused).

Value

A fasterrcnn_model nn_module.

Functions

• model_fasterrcnn_resnet50_fpn(): Faster R-CNN with ResNet-50 FPN

• model_fasterrcnn_resnet50_fpn_v2(): Faster R-CNN with ResNet-50 FPN V2

• model_fasterrcnn_mobilenet_v3_large_fpn(): Faster R-CNN with MobileNet V3 Large FPN

• model_fasterrcnn_mobilenet_v3_large_320_fpn(): Faster R-CNN with MobileNet V3 Large 320 FPN

Task

Object detection over images with bounding boxes and class labels.

Object detection over images with bounding boxes and class labels.

Input Format

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

Available Models

• model_fasterrcnn_resnet50_fpn()

• model_fasterrcnn_resnet50_fpn_v2()

• model_fasterrcnn_mobilenet_v3_large_fpn()

• model_fasterrcnn_mobilenet_v3_large_320_fpn()

See Also

Other object_detection_model: model_facenet

Examples

## Not run: 
library(magrittr)
norm_mean <- c(0.485, 0.456, 0.406) # ImageNet normalization constants, see
# https://pytorch.org/vision/stable/models.html
norm_std  <- c(0.229, 0.224, 0.225)
# Use a publicly available image of an animal
wmc <- "https://upload.wikimedia.org/wikipedia/commons/thumb/"
url <- "e/ea/Morsan_Normande_vache.jpg/120px-Morsan_Normande_vache.jpg"
img <- base_loader(paste0(wmc,url))

input <- img %>%
  transform_to_tensor() %>%
  transform_resize(c(520, 520)) %>%
  transform_normalize(norm_mean, norm_std)
batch <- input$unsqueeze(1)    # Add batch dimension (1, 3, H, W)

# ResNet-50 FPN
model <- model_fasterrcnn_resnet50_fpn(pretrained = TRUE)
model$eval()
pred <- model(batch)$detections
num_boxes <- as.integer(pred$boxes$size()[1])
keep <- seq_len(min(5, num_boxes))
boxes <- pred$boxes[keep, ]$view(c(-1, 4))
labels <- ds$category_names[as.character(as.integer(pred$labels[keep]))]
if (num_boxes > 0) {
  boxed <- draw_bounding_boxes(image, boxes, labels = labels)
  tensor_image_browse(boxed)
}

# ResNet-50 FPN V2
model <- model_fasterrcnn_resnet50_fpn_v2(pretrained = TRUE)
model$eval()
pred <- model(batch)$detections
num_boxes <- as.integer(pred$boxes$size()[1])
keep <- seq_len(min(5, num_boxes))
boxes <- pred$boxes[keep, ]$view(c(-1, 4))
labels <- ds$category_names[as.character(as.integer(pred$labels[keep]))]
if (num_boxes > 0) {
  boxed <- draw_bounding_boxes(image, boxes, labels = labels)
  tensor_image_browse(boxed)
}

# MobileNet V3 Large FPN
model <- model_fasterrcnn_mobilenet_v3_large_fpn(pretrained = TRUE)
model$eval()
pred <- model(batch)$detections
num_boxes <- as.integer(pred$boxes$size()[1])
keep <- seq_len(min(5, num_boxes))
boxes <- pred$boxes[keep, ]$view(c(-1, 4))
labels <- ds$category_names[as.character(as.integer(pred$labels[keep]))]
if (num_boxes > 0) {
  boxed <- draw_bounding_boxes(image, boxes, labels = labels)
  tensor_image_browse(boxed)
}

# MobileNet V3 Large 320 FPN
model <- model_fasterrcnn_mobilenet_v3_large_320_fpn(pretrained = TRUE)
model$eval()
pred <- model(batch)$detections
num_boxes <- as.integer(pred$boxes$size()[1])
keep <- seq_len(min(5, num_boxes))
boxes <- pred$boxes[keep, ]$view(c(-1, 4))
labels <- ds$category_names[as.character(as.integer(pred$labels[keep]))]
if (num_boxes > 0) {
  boxed <- draw_bounding_boxes(image, boxes, labels = labels)
  tensor_image_browse(boxed)
}

## End(Not run)

torchvision documentation built on Nov. 6, 2025, 9:07 a.m.