We write your reusable computer vision tools. 💜

Machine learning metrics for distributed, scalable PyTorch applications.

Retro games for Reinforcement Learning Research

RZDoom - The ZDoom you know and love, only better.

The NetHack Learning Environment

✨ Magical shell history

The Meson Build System

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Taming Transformers for High-Resolution Image Synthesis

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

High resolution fine-grained face editing

Neural Networks Templates Library

A library for neuroscience-inspired navigation and decision making research.

A library for ready-made reinforcement learning agents and reusable components for neat prototyping

Retro Games in Gym

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

OpenMMLab Pose Estimation Toolbox and Benchmark.

Python Implementation of Reinforcement Learning: An Introduction

GZDoom is a feature centric port for all Doom engine games, based on ZDoom, adding an OpenGL renderer and powerful scripting capabilities

Image segmentation code for Monocular Robot Navigation with Self-Supervised Pretrained Vision Transformers.

A tool for Go players: SGF editor, analysis tool, game database and pattern search tool, IGS client

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

A handy guide to financial support for open source

A curated list of awesome computer vision resources

RetinaFace (RetinaFace: Single-stage Dense Face Localisation in the Wild, published in 2019) reimplemented in Tensorflow 2.0, with pretrained weights available !

This is the repo for the work "Where and What: Driver Attention-based Object Detection".