Gopala KR

loop-engineering. Practical patterns, starters & CLI tools for loop engineering with AI coding agents. Design systems that prompt and orchestrate agents (inspired by Addy Osmani and Boris Cherny). Includes loop-audit, loop-init, loop-cost.

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

openai-cookbook. Examples and guides for using the OpenAI API

ChatGPT. Reverse engineered ChatGPT API

pytorch-normalizing-flows. Normalizing flows in PyTorch. Current intended use is education not production.

ru-gpts. Russian GPT3 models.

deepmind-research. This repository contains implementations and illustrative code to accompany DeepMind publications

eht-imaging. Imaging, analysis, and simulation software for radio interferometry

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

neural-mmo. Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"

gpt-2. Code for the paper "Language Models are Unsupervised Multitask Learners"

DRL_based_SelfDrivingCarControl. Deep Reinforcement Learning (DQN) based Self Driving Car Control with Vehicle Simulator

mit-deep-learning. Tutorials, assignments, and competitions for MIT Deep Learning related courses.

hyperlearn. 2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

dopamine. Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

stanford-cs-229-machine-learning. VIP cheatsheets for Stanford's CS 229 Machine Learning

dadsresume. My dad's resume and skills from 1980

vid2vid. Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

tacotron2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Kalman-and-Bayesian-Filters-in-Python. Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.

autokeras. AutoML library for deep learning

deep-voice-conversion. Deep neural networks for voice conversion (voice style transfer) in Tensorflow

robosat. Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, roads, water, clouds

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

serving. A flexible, high-performance serving system for machine learning models

generative-models. research and implementations of Generative Models(GANs, VAEs and Autoregressive models) and their applications

glow. Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

react-developer-roadmap. Roadmap to becoming a React developer

models. A collection of pre-trained, state-of-the-art models in the ONNX format

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

darts. Differentiable architecture search for convolutional and recurrent networks

bad-data-guide. An exhaustive reference to problems seen in real-world data along with suggestions on how to resolve them.

amazon-sagemaker-examples. Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.

scalable_agent. A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

training-data-analyst. Labs and demos for courses for GCP Training (http://cloud.google.com/training).

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.

decaNLP. The Natural Language Decathlon: A Multitask Challenge for NLP

DensePose. A real-time approach for mapping all human pixels of 2D RGB images to a 3D surface-based model of the body

adversarial-robustness-toolbox. Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

neural_renderer. "Neural 3D Mesh Renderer" (CVPR 2018) by H. Kato, Y. Ushiku, and T. Harada.

nlp-architect. A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

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

PhoenixGo. Go AI program which implements the AlphaGo Zero paper

build-your-own-x. Master programming by recreating your favorite technologies from scratch.

horovod. Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

Rainbow. Rainbow: Combining Improvements in Deep Reinforcement Learning

awesome-scalability. The Patterns of Scalable, Reliable, and Performant Large-Scale Systems

gradient-checkpointing. Make huge neural nets fit in memory

tensorflow-wavenet. A TensorFlow implementation of DeepMind's WaveNet paper

tfjs. A WebGL accelerated JavaScript library for training and deploying ML models.

go-internals. A book about the internals of the Go programming language.

ngraph. nGraph has moved to OpenVINO

jetson-reinforcement. Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.

stats337. Readings in applied data science

LeakGAN. The codes of paper "Long Text Generation via Adversarial Training with Leaked Information" on AAAI 2018. Text generation using GAN and Hierarchical Reinforcement Learning.

InstaPy. 📷 Instagram Bot - Tool for automated Instagram interactions

cookiecutter. A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.

snips-nlu. Snips Python library to extract meaning from text

chess-alpha-zero. Chess reinforcement learning by AlphaGo Zero methods.

lucid. A collection of infrastructure and tools for research in neural network interpretability.

Keras-GAN. Keras implementations of Generative Adversarial Networks.

numerical-tours. Numerical Tours of Signal Processing

obfuscated-gradients. Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

dm_control. Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

ENAS-pytorch. PyTorch implementation of "Efficient Neural Architecture Search via Parameters Sharing"

docker-stacks. Ready-to-run Docker images containing Jupyter applications

One-Hundred-Layers-Tiramisu. Keras Implementation of The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation by (Simon Jégou, Michal Drozdzal, David Vazquez, Adriana Romero, Yoshua Bengio)

AlphaPose. Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

wtfpython. What the f*ck Python? 😱

minigo. An open-source implementation of the AlphaGoZero algorithm

cudnn-training. A CUDNN minimal deep learning training code sample using LeNet.

pytorch-qrnn. PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM

cupy. NumPy & SciPy for GPU

self-driving-car. The Udacity open source self-driving car project

pyro. Deep universal probabilistic programming with Python and PyTorch

Flicks. A unit of time defined in C++.

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

ffmpeg-libav-tutorial. FFmpeg libav tutorial - learn how media works from basic to transmuxing, transcoding and more. Translations: 🇺🇸 🇨🇳 🇰🇷 🇪🇸 🇻🇳 🇧🇷 🇷🇺

repo2docker. Turn repositories into Jupyter-enabled Docker images

CapsNet-Tensorflow. A Tensorflow implementation of CapsNet(Capsules Net) in paper Dynamic Routing Between Capsules

deep-neuroevolution. Deep Neuroevolution

geonotebook. A Jupyter notebook extension for geospatial visualization and analysis

Screenshot-to-code. A neural network that transforms a design mock-up into a static website.

KaTeX. Fast math typesetting for the web.

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

DeepRL-Grounding. Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)

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

wav2letter. Facebook AI Research's Automatic Speech Recognition Toolkit

neuraltalk. NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

py-faster-rcnn. Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version

caffe-tensorflow. Caffe models in TensorFlow

nn. Lua

gym. A toolkit for developing and comparing reinforcement learning algorithms.

artistic-videos. Torch implementation for the paper "Artistic style transfer for videos"

R-FCN. R-FCN: Object Detection via Region-based Fully Convolutional Networks

neural-painter. Paint artistic patterns using random neural network.

pytorch-generative-adversarial-networks. A very simple generative adversarial network (GAN) in PyTorch

fcn.berkeleyvision.org. Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.

welcome_tutorials. Various tutorials given for welcoming new students at MILA.

malmo. Project Malmo is a platform for Artificial Intelligence experimentation and research built on top of Minecraft. We aim to inspire a new generation of research into challenging new problems presented by this unique environment. --- For installation instructions, scroll down to *Getting Started* below, or visit the project page for more information:

matconvnet. MatConvNet: CNNs for MATLAB

torchnet. Torch on steroids

videogan. Generating Videos with Scene Dynamics. NIPS 2016.

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

pixel-cnn. Code for the paper "PixelCNN++: A PixelCNN Implementation with Discretized Logistic Mixture Likelihood and Other Modifications"

WassersteinGAN. Python

semantic-segmentation-pytorch. Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

chatbot-retrieval. Dual LSTM Encoder for Dialog Response Generation

cnn-text-classification-tf. Convolutional Neural Network for Text Classification in Tensorflow

DrQA. Reading Wikipedia to Answer Open-Domain Questions

Conditional-PixelCNN-decoder. Tensorflow implementation of Gated Conditional Pixel Convolutional Neural Network

ResNeXt. Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

stargan. StarGAN - Official PyTorch Implementation (CVPR 2018)

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

sonnet. TensorFlow-based neural network library

seq2seq. A general-purpose encoder-decoder framework for Tensorflow

pysc2. StarCraft II Learning Environment

bayesgan. Tensorflow code for the Bayesian GAN (https://arxiv.org/abs/1705.09558) (NIPS 2017)

lab. A customisable 3D platform for agent-based AI research

dnc. A TensorFlow implementation of the Differentiable Neural Computer.

generating-reviews-discovering-sentiment. Code for "Learning to Generate Reviews and Discovering Sentiment"

pointer-generator. Code for the ACL 2017 paper "Get To The Point: Summarization with Pointer-Generator Networks"

DeepMoji. State-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc.

fashion-mnist. A MNIST-like fashion product database. Benchmark :point_down:

batch-ppo. Efficient Batched Reinforcement Learning in TensorFlow

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

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

tensornets. High level network definitions with pre-trained weights in TensorFlow

vision. Datasets, Transforms and Models specific to Computer Vision

improved-gan. Code for the paper "Improved Techniques for Training GANs"

fast-style-transfer-deeplearnjs. Demo of in-browser Fast Neural Style Transfer with deeplearn.js library

sru. Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)

DeepRecommender. Deep learning for recommender systems

DeepNLP-models-Pytorch. Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)

LSTM-Human-Activity-Recognition. Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

imgaug. Image augmentation for machine learning experiments.

Practical_RL. A course in reinforcement learning in the wild

ELF. An End-To-End, Lightweight and Flexible Platform for Game Research

neural-style-tf. TensorFlow (Python API) implementation of Neural Style

OpenNMT. Open Source Neural Machine Translation in Torch (deprecated)

deep-learning-keras-tensorflow. Introduction to Deep Neural Networks with Keras and Tensorflow

mlpack. mlpack: a fast, header-only C++ machine learning library

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

DenseNet. Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

iGAN. Interactive Image Generation via Generative Adversarial Networks

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

deepo. Setup and customize deep learning environment in seconds.

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

edward. A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

Paddle-Lite. PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）

keras-js. Run Keras models in the browser, with GPU support using WebGL

neurojs. A JavaScript deep learning and reinforcement learning library.

pix2pix. Image-to-image translation with conditional adversarial nets

handson-ml. ⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.

CycleGAN. Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

MLAlgorithms. Minimal and clean examples of machine learning algorithms implementations

apollo. An open autonomous driving platform

CoreNLP. CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.

turicreate. Turi Create simplifies the development of custom machine learning models.

skorch. A scikit-learn compatible neural network library that wraps PyTorch

kubeflow. Machine Learning Toolkit for Kubernetes

convnet-benchmarks. Easy benchmarking of all publicly accessible implementations of convnets

ganhacks. starter from "How to Train a GAN?" at NIPS2016

char-rnn. Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

sentiment-discovery. Unsupervised Language Modeling at scale for robust sentiment classification

sling. SLING - A natural language frame semantics parser

carla. Open-source simulator for autonomous driving research.

AirSim. Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

cosmos. World's largest Contributor driven code dataset | Used in Quark Search Engine, @OpenGenus IQ, OpenGenus Visual Project

deepvariant. DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.

pix2pixHD. Synthesizing and manipulating 2048x1024 images with conditional GANs

FaderNetworks. Fader Networks: Manipulating Images by Sliding Attributes - NIPS 2017

seq2seq. Minimal Seq2Seq model with Attention for Neural Machine Translation in PyTorch

probtorch. Probabilistic Torch is library for deep generative models that extends PyTorch

densecap. Dense image captioning in Torch

fb.resnet.torch. Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

tf-adversarial. Adversarial networks in TensorFlow

marvin. Marvin: A Minimalist GPU-only N-Dimensional ConvNets Framework

faster_rcnn. Faster R-CNN

Theano-Tutorials. Bare bones introduction to machine learning from linear regression to convolutional neural networks using Theano.

scholar.py. A parser for Google Scholar, written in Python

reinforcement-learning. Minimal and Clean Reinforcement Learning Examples

Qix. Machine Learning、Deep Learning、PostgreSQL、Distributed System、Node.Js、Golang

deep-image-prior. Image restoration with neural networks but without learning.

DeepSpeech. DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

pytudes. Python programs, usually short, of considerable difficulty, to perfect particular skills.

dockerfiles. Various Dockerfiles I use on the desktop and on servers.

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

torontoai. A list of meetups, conferences, companies, and influencers in the Toronto Artificial Intelligence, Deep Learning, Neural Networks, and Machine Learning space.

Neural-Style-Transfer. Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+

benchmark_results. Visual Tracking Paper List

handong1587.github.io. CSS

Stack-RNN. This is the code used for the paper "Inferring algorithmic patterns with a stack augmented recurrent network", by Armand Joulin and Tomas Mikolov.

bAbI-tasks. Task generation for testing text understanding and reasoning

nlp_tasks. Natural Language Processing Tasks and References

dcgan_code. Deep Convolutional Generative Adversarial Networks

SqueezeNet. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters

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

deep-belief-network. A Python implementation of Deep Belief Networks built upon NumPy and TensorFlow with scikit-learn compatibility

React-Native-Apps. Curated List of Open Source React Native Apps. Curation curtesy of