Robust Speech Recognition via Large-Scale Weak Supervision

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

Image-to-Image Translation in PyTorch

A list of all named GANs!

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

Hackable and optimized Transformers building blocks, supporting a composable construction.

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Pytorch implementation of convolutional neural network visualization techniques

🔥 2D and 3D Face alignment library build using pytorch

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

⚡️ Python client for the unofficial ChatGPT API with auto token regeneration, conversation tracking, proxy support and more.

Simple PyTorch Tutorials Zero to ALL!

3D ResNets for Action Recognition (CVPR 2018)

A library of reinforcement learning components and agents

Semantic Segmentation Architectures Implemented in PyTorch

Accelerated deep learning R&D

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

FFCV: Fast Forward Computer Vision (and other ML workloads!)

Implementation of Convolutional LSTM in PyTorch.

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Python Multi-Agent Reinforcement Learning framework

A very simple generative adversarial network (GAN) in PyTorch

A memory-efficient implementation of DenseNets

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Dilated Residual Networks

Video classification tools using 3D ResNet

👼 Morph faces with Python, Numpy, Scipy