FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Graph Neural Network Library for PyTorch

Datasets, Transforms and Models specific to Computer Vision

Python Implementation of Reinforcement Learning: An Introduction

🐍 Geometric Computer Vision Library for Spatial AI

An elegant PyTorch deep reinforcement learning library.

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Depth-Aware Video Frame Interpolation (CVPR 2019)

95.47% on CIFAR10 with PyTorch

Progressive Growing of GANs for Improved Quality, Stability, and Variation

An easy to use PyTorch to TensorRT converter

3D ResNets for Action Recognition (CVPR 2018)

A collection of loss functions for medical image segmentation

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

Flops counter for neural networks in pytorch framework

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia, Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Adaptive Experimentation Platform

Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

Medical imaging processing for AI applications.

A CV toolkit for my papers.

An MIT License of YOLOv9, YOLOv7, YOLO-RD

Synchronized Batch Normalization implementation in PyTorch.

In-Place Activated BatchNorm for Memory-Optimized Training of DNNs

A New Padding Scheme: Partial Convolution based Padding

KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

K3D lets you create 3D plots backed by WebGL with high-level API (surfaces, isosurfaces, voxels, mesh, cloud points, vtk objects, volume renderer, colormaps, etc). The primary aim of K3D-jupyter is…