Torchvisiontransforms
Is this your brand? Claim it — free, and takes a minute with your work email.
Overview
Tagline Brand's website · 2026-10-04
Unified API for transforming multiple data types (images, videos, boxes, masks, keypoints) coherently; significant performance improvements in v2; deep integration with the PyTorch framework; backward compatibility with prior versions.
Description Brand's website · 2026-10-04
A module within the PyTorch Torchvision library that provides common computer vision transformations and data augmentation tools for images, videos, bounding boxes, masks, and keypoints. It emphasizes performance and versatility, especially with its v2 iteration.
Offerings
Core capabilities Brand's website · 2026-10-04
- Computer vision data transformation and augmentation tools for various data types (images
- videos
- bounding boxes
- masks
- keypoints).
Pricing Brand's website · 2026-10-04
Free and open-source (as part of the PyTorch ecosystem).
Audience
Target industry Brand's website · 2026-10-04
Machine learning engineers, deep learning researchers, data scientists, and computer vision developers using the PyTorch framework.
Landscape
Competitors Brand's website · 2026-10-04
- Albumentations
- Keras Preprocessing Layers
- Imgaug
- TensorFlow tf.image operations
Is this your business?
The information above is publicly sourced — assembled by Optimly from Torchvisiontransforms's website and public pages.
Claim this profile to publish your own verified Business Profile and speak for Torchvisiontransforms across the index.
Claim Torchvisiontransforms — free →Page last updated 2026-10-04.