Chaoqi Wang

ThunderKittens. Tile primitives for speedy kernels

ml-engineering. Machine Learning Engineering Open Book

grok-1. Grok open release

TransformersCanDoBayesianInference. Official Implementation of "Transformers Can Do Bayesian Inference", the PFN paper

brax. Massively parallel rigidbody physics simulation on accelerator hardware.

acme. A library of reinforcement learning components and agents

jaxls. Sparse nonlinear least squares in JAX

jaxton. 100 exercises to learn JAX

annotated_latex_equations. Examples of how to create colorful, annotated equations in Latex using Tikz.

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

predictive-correlation-benchmark. Python

submitit. Python 3.8+ toolbox for submitting jobs to Slurm

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

Follow-the-Ridge. Minimax Optimization, Stackelberg Games, Generative Adversarial Networks

cvxpylayers. Differentiable convex optimization layers

backpack. This repository is no longer maintained. Check

botorch. Bayesian optimization in PyTorch

matplotlib-cheatsheet. Matplotlib 3.1 cheat sheet.

residual-flows. code for "Residual Flows for Invertible Generative Modeling".

nngp. Deep neural network kernel for Gaussian process

BatchBALD. Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning.

omniboard. Web-based dashboard for Sacred

sacred. Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

self-tuning-networks. Code for Self-Tuning Networks (ICLR 2019) https://arxiv.org/abs/1903.03088

MAX. Code for reproducing experiments in Model-Based Active Exploration, ICML 2019

Efficient-Deep-Learning. Collection of recent methods on (deep) neural network compression and acceleration.

Weight-Decay. Regularization, Neural Network Training Dynamics

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

NoisyNaturalGradient. TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC".

Ax. Adaptive Experimentation Platform

neural-tangents. Fast and Easy Infinite Neural Networks in Python

FBNN. Code for "Functional variational Bayesian neural networks" (https://arxiv.org/abs/1903.05779)

snip. Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.

paper-tips-and-tricks. Best practice and tips & tricks to write scientific papers in LaTeX, with figures generated in Python or Matlab.

lottery-ticket-hypothesis. A reimplementation of "The Lottery Ticket Hypothesis" (Frankle and Carbin) on MNIST.

pytorch-OpCounter. Count the MACs / FLOPs of your PyTorch model.

tensorly. TensorLy: Tensor Learning in Python.

pytorch-tensor-decompositions. PyTorch implementation of [1412.6553] and [1511.06530] tensor decomposition methods for convolutional layers.

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

ffjord. code for "FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models".

pytorch-a2c-ppo-acktr-gail. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

natural-gradients. Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)

rethinking-network-pruning. Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

BayesianOptimization. A Python implementation of global optimization with gaussian processes.

SceneGraphParser. A python toolkit for parsing captions (in natural language) into scene graphs (as symbolic representations).

pytorch_geometric. Graph Neural Network Library for PyTorch

graph_nets. Build Graph Nets in Tensorflow

compcaption_neurips2018. A Neural Compositional Paradigm for Image Captioning

graph_comb_opt. Implementation of "Learning Combinatorial Optimization Algorithms over Graphs"

hessian. hessian in pytorch

vmf_vae_nlp. Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"

EC-Net. EC-Net: an Edge-aware Point set Consolidation Network, ECCV, 2018

Pixel2Mesh. Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images. In ECCV2018.

conceptnet5. Code for building ConceptNet from raw data.

stanford-cs193g-sp2010. This is an archive of materials produced for an introductory class on CUDA programming at Stanford University in 2010

UnsupervisedMT. Phrase-Based & Neural Unsupervised Machine Translation

polyrnn-pp-pytorch. PyTorch training/tool code for Polygon-RNN++ (CVPR 2018)

von_mises_fisher. Model your data with the Von Mises-Fisher distribution in Python

Stack-Captioning. Stack-Captioning: Coarse-to-Fine Learning for Image Captioning

NLP-progress. Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

pointer-network-tensorflow. TensorFlow implementation of "Pointer Networks"

visdial-rl. PyTorch code for Learning Cooperative Visual Dialog Agents using Deep Reinforcement Learning

zero-shot-gcn. Zero-Shot Learning with GCN (CVPR 2018)

gdown. Google Drive public file downloader when curl/wget fails.

sg2im. Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018

Pytorch-UNet. PyTorch implementation of the U-Net for image semantic segmentation with high quality images

models. Models and examples built with TensorFlow

few-shot-ssl-public. Meta Learning for Semi-Supervised Few-Shot Classification

topicsne. t-SNE experiments in pytorch

FewShot-CVPR. Few-Shot Image Recognition by Predicting Parameters from Activations

pytorch-fcn. PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

CIFAR-10.1. Release of CIFAR-10.1, a new test set for CIFAR-10.

StackNN. Experiments with differentiable stacks and queues in PyTorch

Few-shot-Meta-learning-papers. Recent few-shot meta-learning papers

low-shot-shrink-hallucinate. Presenting Low-shot Visual Recognition by Shrinking and Hallucinating Features

pytorch-maml. PyTorch implementation of MAML: https://arxiv.org/abs/1703.03400

soundnet. SoundNet: Learning Sound Representations from Unlabeled Video. NIPS 2016

higgsfield. Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

review_net. Review Network for Caption Generation

visual-attribution. Pytorch Implementation of recent visual attribution methods for model interpretability

Meta-Learning-Papers. Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning

torchfold. Tools for PyTorch

vqa-counting. [ICLR 2018] Learning to Count Objects in Natural Images for Visual Question Answering

pytorch-template. PyTorch deep learning projects made easy.

Tensorflow-Project-Template. A best practice for tensorflow project template architecture.

REGAN. ReGAN: Sequence GAN using RE[INFORCE|LAX|BAR] based PG estimators

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

CoDraw. CoDraw dataset

drn. Dilated Residual Networks

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

gluon-cv. Gluon CV Toolkit

noisy-K-FAC. Natural Gradient, Variational Inference

tqdm. :zap: A Fast, Extensible Progress Bar for Python and CLI

gluon-nlp. NLP made easy

mxnet-the-straight-dope. An interactive book on deep learning. Much easy, so MXNet. Wow. [Straight Dope is growing up] ---> Much of this content has been incorporated into the new Dive into Deep Learning Book available at https://d2l.ai/.

CS-Notes. :books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

Matterport3DSimulator. AI Research Platform for Reinforcement Learning from Real Panoramic Images.

NRLPapers. Must-read papers on network representation learning (NRL) / network embedding (NE)

CliqueNet. Convolutional Neural Networks with Alternately Updated Clique (to appear in CVPR 2018)

bottom-up-attention. Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome

alpha-zero-general. A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more

nvvl. A library that uses hardware acceleration to load sequences of video frames to facilitate machine learning training

pytorch-rnng. Python

NoisyNaturalGradient. Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference"

TCN. Sequence modeling benchmarks and temporal convolutional networks

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

treelstm.pytorch. Tree LSTM implementation in PyTorch

unsupervised-treelstm. Python

NA-NMT. Non-autoregressive Neural Machine Translation (not a full version)

nn4nlp-code. Code Samples from Neural Networks for NLP

iter-reason. Code for Iterative Reasoning Paper (CVPR 2018)

polyrnn-pp. Inference Code for Polygon-RNN++ (CVPR 2018)

nonauto-nmt. PyTorch Implementation of "Non-Autoregressive Neural Machine Translation"

NeuralBabyTalk. Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"

active-learning. Python

detectorch. Detectorch - detectron for PyTorch

pytorch-dilated-rnn. Dilated RNNs in pytorch

meta-optim-public. Understanding Short-Horizon Bias in Stochastic Meta-Optimization

pytorch_structure2vec. pytorch implementation of structure2vec (https://arxiv.org/abs/1603.05629)

wide-resnet.pytorch. Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch

anchor. Code for "High-Precision Model-Agnostic Explanations" paper

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

python3_with_pleasure. A short guide on features of Python 3 with examples

influence-release. Jupyter Notebook

tiny-dnn. header only, dependency-free deep learning framework in C++14

tech-interview-handbook. Curated coding interview preparation materials for busy software engineers

gradient-checkpointing. Make huge neural nets fit in memory

blocksparse. Efficient GPU kernels for block-sparse matrix multiplication and convolution

tensorforce. Tensorforce: a TensorFlow library for applied reinforcement learning

House3D. a Realistic and Rich 3D Environment

TensorFlow-Tutorials. TensorFlow Tutorials with YouTube Videos

Capsule-Network-Tutorial. Pytorch easy-to-follow Capsule Network tutorial

neural-combinatorial-rl-pytorch. PyTorch implementation of Neural Combinatorial Optimization with Reinforcement Learning https://arxiv.org/abs/1611.09940

inferno. A utility library around PyTorch

pytorch-custom-cuda-tutorial. Tutorial for building a custom CUDA function for Pytorch

cider. python codes for CIDEr - Consensus-based Image Caption Evaluation

MemNN. Memory Networks implementations

MARL-Papers. Paper list of multi-agent reinforcement learning (MARL)

dynet. DyNet: The Dynamic Neural Network Toolkit

skip-thoughts. The first public PyTorch implementation of Skip-Thought Vectors

gpss-research. Kernel structure discovery research code - likely to be unstable

gp-structure-search. TeX

pytorch-book. PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch：入门与实战》)

simple-faster-rcnn-pytorch. A simplified implemention of Faster R-CNN that replicate performance from origin paper

AdaptiveAttention. Implementation of "Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning"

Recurrent-Highway-Hypernetworks-NIPS. Cleaned original source code from my NIPS publication

pytorch-generative-model-collections. Collection of generative models in Pytorch version.

Image-Text-Papers. Image Caption and Text to Image papers.

icml2016. Generative Adversarial Text-to-Image Synthesis

dfn. Jupyter Notebook

autogradpp. Direct C++ Interface to PyTorch

GibbsNet. Implementation of paper "GibbsNet: Iterative Adversarial Inference for Deep Graphical Models" in PyTorch

Paper_Reading_List. Recommended Papers. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Learning (cs.LG)

neural-editor. Repository for "Generating Sentences by Editing Prototypes"

nmtpytorch. Sequence-to-Sequence Framework in PyTorch

neuraltalk2. Efficient Image Captioning code in Torch, runs on GPU

imgaug. Image augmentation for machine learning experiments.

extension-ffi. Examples of C extensions for PyTorch

tutorials. PyTorch tutorials.

densenet-pytorch. A PyTorch Implementation for Densely Connected Convolutional Networks (DenseNets)

densenet.pytorch. A PyTorch implementation of DenseNet.

nmn-pytorch. Neural Module Network for VQA in Pytorch

nips_2017. videos, slides, and others from NIPS 2017

cupy. NumPy & SciPy for GPU

Generative-Latent-Optimization-Tensorflow. Tensorflow implementation of Generative Latent Optimization (GLO) proposed by Facebook AI Research

karel. Karel dataset for program synthesis and program induction

deepnet. Implementation of some deep learning algorithms.

mixup_pytorch. A PyTorch implementation of the paper Mixup: Beyond Empirical Risk Minimization in PyTorch

pyro. Deep universal probabilistic programming with Python and PyTorch

Mask_RCNN. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

mltrain-nips-2017. This repository contains all the material for the MLTrain NIPS workshop

MAgent. A Platform for Many-Agent Reinforcement Learning

VQ-VAE. VQ-VAE implementation / pytorch

tensorpack. A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

SPICE. Semantic Propositional Image Caption Evaluation

deep-learning-papers. Papers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.

pytorch.rl.learning. for learning reinforcement learning using PyTorch.

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

Pytorch-Sketch-RNN. a pytorch implementation of https://arxiv.org/abs/1704.03477

magenta. Magenta: Music and Art Generation with Machine Intelligence

Awesome-pytorch-list. A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.

self-critical.pytorch. Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.

dlsys-course.github.io. Deep learning system course

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

osim-rl. Reinforcement learning environments with musculoskeletal models

pytorch-faster-rcnn. pytorch1.0 updated. Support cpu test and demo. (Use detectron2, it's a masterpiece)

tangent. Source-to-Source Debuggable Derivatives in Pure Python

numerical-linear-algebra. Free online textbook of Jupyter notebooks for fast.ai Computational Linear Algebra course

qpth. A fast and differentiable QP solver for PyTorch.

autograd. Efficiently computes derivatives of NumPy code.

pymc. Bayesian Modeling and Probabilistic Programming in Python

deep-reinforcement-learning-papers. A list of recent papers regarding deep reinforcement learning

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

pytorch-rl. Deep Reinforcement Learning with pytorch & visdom

AdversarialNetsPapers. Awesome paper list with code about generative adversarial nets

ggnn. Gated Graph Sequence Neural Networks

clevr-iep. Inferring and Executing Programs for Visual Reasoning

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

reinforcement-learning-an-introduction. Python Implementation of Reinforcement Learning: An Introduction