Tensors and Dynamic neural networks in Python with strong GPU acceleration

Animation engine for explanatory math videos

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

Image-to-Image Translation in PyTorch

Datasets, Transforms and Models specific to Computer Vision

Image augmentation for machine learning experiments.

🐍 Geometric Computer Vision Library for Spatial AI

StarGAN - Official PyTorch Implementation (CVPR 2018)

High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.

A highly efficient implementation of Gaussian Processes in PyTorch

Accelerated deep learning R&D

Caffe models in TensorFlow

Differentiable convex optimization layers

The Places365-CNNs for Scene Classification

Unsupervised Image-to-Image Translation

A very simple generative adversarial network (GAN) in PyTorch

Photographic Image Synthesis with Cascaded Refinement Networks

Python tools for working with KITTI data.

Learning diverse image-to-image translation from unpaired data

Convert KITTI dataset to ROS bag file the easy way!

A toolkit for robot learning research.

Geometry-Aware Learning of Maps for Camera Localization (CVPR2018)

Python implementation of SO2, SE2, SO3, and SE3 matrix Lie groups using numpy or pytorch

Differentiable RANSAC: Learning Robust Line Fitting

Non-linear least-squares SLAM in Python using scipy and numpy. Modelled after Google's Ceres solver.

Canonical Appearance Transformations

Bayesian CNN Sun Detector