Learn R Programming

torchvision

torchvision is an extension for torch providing image loading, transformations, common architectures for computer vision, pre-trained weights and access to commonly used datasets.

Installation

The CRAN release can be installed with:

install.packages("torchvision")

You can install the development version from GitHub with:

remotes::install_github("mlverse/torchvision@main")

Copy Link

Version

Install

install.packages('torchvision')

Monthly Downloads

6,126

Version

0.8.0

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Repository

https://github.com/mlverse/torchvision

Homepage

https://torchvision.mlverse.org

Maintainer

Daniel Falbel

Last Published

November 6th, 2025

Functions in torchvision (0.8.0)

Batched Non-maximum Suppression (NMS)

draw_segmentation_masks

Draw segmentation masks

coco_caption_dataset

COCO Caption Dataset

eurosat_dataset

EuroSAT datasets

.rename_mobilenet_v3_state_dict

Rename state_dict keys to match current MobileNetV3 model structure

coco_polygon_to_mask

Convert COCO polygon to mask tensor (Robust Version)

cifar10_dataset

Draws Keypoints

draw_bounding_boxes

Draws bounding boxes on image.

clip_boxes_to_image

Clip Boxes to Image

coco_detection_dataset

COCO Detection Dataset

image_folder_dataset

Create an image folder dataset

generalized_box_iou

Generalized Box IoU

FER-2013 Facial Expression Dataset

fgvc_aircraft_dataset

FGVC Aircraft Dataset

flowers102_dataset

Oxford Flowers 102 Dataset

flickr_caption_dataset

Flickr Caption Datasets

Load an Image using ImageMagick

MNIST and Derived Datasets

model_fasterrcnn

Faster R-CNN Models

model_inception_v3

Inception v3 model

imagenet_classes

ImageNet Class Labels

AlexNet Model Architecture

model_fcn_resnet

Fully Convolutional Network for Semantic Segmentation

model_efficientnet_v2

EfficientNetV2 Models

MTCNN Face Detection Networks

Vision Transformer Implementation

places365_dataset

Places365 Dataset

model_mobilenet_v3

MobileNetV3 Model

pascal_voc_datasets

Pascal VOC Datasets

Non-maximum Suppression (NMS)

ResNet implementation

model_mobilenet_v2

MobileNetV2 Model

model_deeplabv3

DeepLabV3 Models

model_efficientnet

EfficientNet Models

oxfordiiitpet_dataset

Oxford-IIIT Pet Classification Datasets

oxfordiiitpet_segmentation_dataset

Oxford-IIIT Pet Segmentation Dataset

ConvNeXt Implementation

VGG implementation

tensor_image_display

Display image tensor

tensor_image_browse

Display image tensor

rf100_medical_collection

RoboFlow 100 Medical dataset Collection

rf100_infrared_collection

RoboFlow 100 Infrared dataset Collection

rf100_underwater_collection

RoboFlow 100 Underwater dataset Collection

rf100_peixos_segmentation_dataset

RF100 Peixos Segmentation Dataset

transform_adjust_saturation

Adjust the color saturation of an image

remove_small_boxes

Remove Small Boxes

rf100_biology_collection

RoboFlow 100 Biology dataset Collection

transform_adjust_hue

Adjust the hue of an image

transform_color_jitter

Randomly change the brightness, contrast and saturation of an image

transform_convert_image_dtype

Convert a tensor image to the given dtype and scale the values accordingly

transform_center_crop

Crops the given image at the center

transform_affine

Apply affine transformation on an image keeping image center invariant

transform_grayscale

Convert image to grayscale

transform_hflip

Horizontally flip a PIL Image or Tensor

transform_adjust_contrast

Adjust the contrast of an image

transform_normalize

Normalize a tensor image with mean and standard deviation

transform_adjust_gamma

Adjust the gamma of an RGB image

transform_linear_transformation

Transform a tensor image with a square transformation matrix and a mean_vector computed offline

rf100_document_collection

RF100 Document Collection Datasets

transform_random_affine

Random affine transformation of the image keeping center invariant

transform_random_apply

Apply a list of transformations randomly with a given probability

rf100_damage_collection

RoboFlow 100 Damages dataset Collection

transform_random_resized_crop

Crop image to random size and aspect ratio

transform_random_perspective

Random perspective transformation of an image with a given probability

Crop the given image at specified location and output size

transform_random_order

Apply a list of transformations in a random order

Pad the given image on all sides with the given "pad" value

tiny_imagenet_dataset

Tiny ImageNet dataset

transform_vflip

Vertically flip a PIL Image or Tensor

vision_make_grid

A simplified version of torchvision.utils.make_grid

whoi_plankton_dataset

WHOI Plankton Datasets

transform_adjust_brightness

Adjust the brightness of an image

transform_random_horizontal_flip

Horizontally flip an image randomly with a given probability

transform_perspective

Perspective transformation of an image

transform_random_vertical_flip

Vertically flip an image randomly with a given probability

transform_random_rotation

Rotate the image by angle

transform_resize

Resize the input image to the given size

transform_resized_crop

Crop an image and resize it to a desired size

transform_random_erasing

Randomly selects a rectangular region in an image and erases its pixel values

transform_to_tensor

Convert an image to a tensor

transform_random_grayscale

Randomly convert image to grayscale with a given probability

transform_ten_crop

Crop an image and the flipped image each into four corners and a central crop

transform_five_crop

Crop image into four corners and a central crop

whoi_small_coralnet_dataset

Coralnet Dataset

transform_rotate

Angular rotation of an image

transform_rgb_to_grayscale

Convert RGB Image Tensor to Grayscale

transform_random_choice

Apply single transformation randomly picked from a list

transform_random_crop

Crop the given image at a random location

box_xyxy_to_xywh

box_xyxy_to_xywh

box_xyxy_to_cxcywh

box_xyxy_to_cxcywh

box_cxcywh_to_xyxy

box_cxcywh_to_xyxy

box_xywh_to_xyxy

box_xywh_to_xyxy

caltech_dataset

Caltech Datasets