🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Models and examples built with TensorFlow

Deep Learning for humans

DeepFaceLab is the leading software for creating deepfakes.

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

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

Deezer source separation library including pretrained models.

Code for the paper "Language Models are Unsupervised Multitask Learners"

Magenta: Music and Art Generation with Machine Intelligence

Luigi is a Python module that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built in.

Code samples for my book "Neural Networks and Deep Learning"

🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…

Bringing Old Photo Back to Life (CVPR 2020 oral)

A MNIST-like fashion product database. Benchmark 👇

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020. For HD commercial model, please try out Sync Labs

Node.js native addon build tool

NumPy aware dynamic Python compiler using LLVM

Ongoing research training transformer models at scale

AWS SDK for Python

A PyTorch implementation of the Transformer model in "Attention is All You Need".

A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

MicroK8s is a small, fast, single-package Kubernetes for datacenters and the edge.

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Code for the paper "Jukebox: A Generative Model for Music"

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR.

Flax is a neural network library for JAX that is designed for flexibility.

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime