Karanbir Chahal

egpu-switcher. 🖥🐧 Setup script for eGPUs in Linux (X.Org)

archimedes. C++20 reflection via code generation

pypose. A library for differentiable robotics on manifolds.

awesome-visual-slam. :books: The list of vision-based SLAM / Visual Odometry open source, blogs, and papers

isaac_mission_dispatch. VDA5050-compatible cloud service for fleet mission dispatch

NVISII. C++

nvdiffrec. Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

cvat. Computer Vision Annotation Tool (CVAT) is a leading platform for building high-quality visual datasets for vision AI. It offers open-source, cloud, and enterprise products, as well as labeling services, for image, video, and 3D annotation with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.

phoneFinder. A small Mask RCNN prototype that learn to detect a phone in an image

node-feature-discovery. Node feature discovery for Kubernetes

decision-transformer. Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

vision-based_estimations. Vision-based Robot 3D Poses and Velocities Estimation

proto. Proto-RL: Reinforcement Learning with Prototypical Representations

rlstructures. RLStructures is a library to facilitate the implementation of new reinforcement learning algorithms. It includes a library, a tutorial, and different RL algorithms provided as examples.

stylegan2-pytorch. Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

ferm. FERM: A Framework for Efficient Robotic Manipulation

dynamo-simulator. An implementation of Dynamo Key Value Store in Python. One of my favorite projects !

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

envoy_queue_detection. Detecting SLA violations using Envoy proxies.

noreward-rl. [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning

OpenAI-GYM-CarRacing-DQN. Train a DQN Agent to play CarRacing 2d using TensorFlow and Keras.

rlpyt. Reinforcement Learning in PyTorch

PlaNet. Deep Planning Network: Control from pixels by latent planning with learned dynamics

hydra. Hydra is a framework for elegantly configuring complex applications

DeepRL. Deep RL algorithms in Pytorch

p4c-xdp. Backend for the P4 compiler targeting XDP

nyu-systems-seminar. The NYU Systems Seminar

grpc. C++ based gRPC (C++, Python, Ruby, Objective-C, PHP, C#)

fa20-lab3-code. HTML

cloudflare-2020-general-engineering-assignment.

data-science-list. A guide-book to get familiar and started on various technologies and tools in the Data Science space

lambda-networks. Implementation of LambdaNetworks, a new approach to image recognition that reaches SOTA with less compute

memformer. Implementation of Memformer, a Memory-augmented Transformer, in Pytorch

pytorch_sac_ae. PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)

SuperPoint. Efficient neural feature detector and descriptor

cvml_project. Projects and application using computer vision and machine learning

monodepth2. DL project: Find monocular depth from videos

awesome-scalability. :bookmark: Everyday-Updated Reading List For Designing High Scalability :cherries:, High Availability :fire:, High Stability :mount_fuji: Back-End Systems - Pull Requests Are Greatly Welcome :two_men_holding_hands: I Hope You Will Find This Project Helpful :four_leaf_clover: Please Help Me Share It To More People :heart: Thank You - 谢谢 - धन्यवाद - ধন্যবাদ - Спасибо - شكرا - Merci - Gracias - Danke - ありがとう - Cảm Ơn! :bow:

manifold. A model-agnostic visual debugging tool for machine learning

awesome-mlops. A curated list of references for MLOps

Atlas. Atlas: End-to-End 3D Scene Reconstruction from Posed Images

applied-ml. 📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

drq. DrQ: Data regularized Q

pytorch_sac. PyTorch implementation of Soft Actor-Critic (SAC)

reprieve. A library for evaluating representations.

garage. A toolkit for reproducible reinforcement learning research.

domain-randomizer. A standalone library to randomize various OpenAI Gym Environments

cluster-support. Python

Prince-Set-UP. NYU Prince set up

hindsight-experience-replay. This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

pytorch_geometric. Graph Neural Network Library for PyTorch

rlkit. Collection of reinforcement learning algorithms

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

normalizing_flows. Pytorch implementations of density estimation algorithms: BNAF, Glow, MAF, RealNVP, planar flows

SuperGluePretrainedNetwork. SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

paxos-go. Implementation of Paxos Algorithm

probabilistic_robotics. solution of exercises of the book "probabilistic robotics"

packnet-sfm. TRI-ML Monocular Depth Estimation Repository

driving-dirty. End-to-end Multi-Camera View Parsing to Top Down Object Detection On Road Maps

mono-semantic-occupancy. Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks

ssl_project. Final project on self-supervised learning for DL course

kornia. 🐍 Geometric Computer Vision Library for Spatial AI

saycam-metric-learning. Temporal SimCLR - A Variation of SimCLR for Video Datasets

one-fourth-labs-deep-learning. Code and Documents related to Deep Learning Course at padh.ai

fashion-product-classification. Classification of fashion product images using transfer learning techniques

rad. RAD: Reinforcement Learning with Augmented Data

pseudo_lidar. (CVPR 2019) Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

PSMNet. Pyramid Stereo Matching Network (CVPR2018)

monolayout. MonoLayout: Amodal Scene Layout from a single image

mdn_jax_tutorial. Mixture Density Networks (Bishop, 1994) tutorial in JAX

Malloc-Implementations. A collection of memory allocators

Colab-Editor. Credt-project

pirl_pytorch. Implementation of Pre-text invariant representation learning algorithm in pytorch

dads. Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.

simclr. SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

SimCLR. PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

SimCLR. PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations by T. Chen et al.

mythread_lib. Our own thread library similar to pthreads

random-network-distillation. Code for the paper "Exploration by Random Network Distillation"

SuperMalloc. A Super Fast Multithreaded malloc() for 64-bit Machines

loss-landscape. Code for visualizing the loss landscape of neural nets

mbbl. Python

world-models. Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch

imagenette. A smaller subset of 10 easily classified classes from Imagenet, and a little more French

jiant. jiant is an nlp toolkit

Hoard. The Hoard Memory Allocator: A Fast, Scalable, and Memory-efficient Malloc for Linux, Windows, and Mac.

pg-is-all-you-need. Policy Gradient is all you need! A step-by-step tutorial for well-known PG methods.

rainbow-is-all-you-need. Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow

amdim-public. Public repo for Augmented Multiscale Deep InfoMax representation learning

python-guide. Python best practices guidebook, written for humans.

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

manim. Animation engine for explanatory math videos

NYU-DLSP20. NYU Deep Learning Spring 2020

SlowFast. PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

tokenizers. 💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

collusive-retweeters-TIST-2020. Analyzing and Detecting Collusive Users Involved in Blackmarket Retweeting Activities (ACM TIST 2020)

self_supervised_bird_classification. Explores jigsaw puzzles solvinig as pre-text task for fine grained classification for bird species identification (Implemented with pyTorch)

MathsDL-spring19. Mathematics of Deep Learning, Courant Insititute, Spring 19

distiller. A large scale study of Knowledge Distillation.

autovc. AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

StyleGAN-Resolution-Convertor. A Google Colab notebook to convert your low-resolution StyleGAN models into higher-resolution checkpoints so you can continue training!

open-nsynth-super. Open NSynth Super is an experimental physical interface for the NSynth algorithm

MusicTransformer-pytorch. implementation of music transformer with pytorch (ICLR2019)

fall-2019-easy-nyu. JavaScript

Miniworld. Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

OpenSfM. Open source Structure-from-Motion pipeline

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

essence. AutoDiff DAG constructor, built on numpy and Cython. A Neural Turing Machine and DeepQ agent run on it. Clean code for educational purpose.

sha-rnn. Single Headed Attention RNN - "Stop thinking with your head"

machine-learning-systems-design. A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`

structure_knowledge_distillation. The official code for the paper 'Structured Knowledge Distillation for Semantic Segmentation'. (CVPR 2019 ORAL) and extension to other tasks.

RepDistiller. [ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

overhaul-distillation. Official PyTorch implementation of "A Comprehensive Overhaul of Feature Distillation" (ICCV 2019)

RKD. Official pytorch Implementation of Relational Knowledge Distillation, CVPR 2019

image_transformer. Pytorch implementation of the image transformer for unconditional image generation

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

torchskeleton. Optimized Utilities for PyTorch

deep-learning-project-template. Pytorch Lightning code guideline for conferences

r2c. Recognition to Cognition Networks (code for the model in "From Recognition to Cognition: Visual Commonsense Reasoning", CVPR 2019)

vilbert_beta. Jupyter Notebook

VMZ. VMZ: Model Zoo for Video Modeling

abstract-reasoning-matrices. Progressive matrices dataset, as described in: Measuring abstract reasoning in neural networks (Barrett*, Hill*, Santoro*, Morcos, Lillicrap), ICML2018

schedge. API for NYU's course catalog

nni. An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

new-grads-2020. A collection of new grad roles for 2020

traffic-signs. Building a CNN based traffic signs classifier.

imbalanced-dataset-sampler. A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

gtsrb-pytorch. PyTorch implementation of Kaggle GTSRB challenge with 99.8% accuracy

traffic-sign-detection-homework. nyu-cv-fall-2017 assignment 3

brevitas. Brevitas: neural network quantization in PyTorch

captum. Model interpretability and understanding for PyTorch

DeepLearningExamples. State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.

hpc. A quick reference to access NYU High Performance Computing

fair-sslime. FAIR Self-Supervised Learning Integrated Multi-modal Environment (SSLIME)

arxiv-sanity-preserver. Web interface for browsing, search and filtering recent arxiv submissions

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/.

kafkapoc. Exploring the innards of Sarama library for Kafka. Language used is Golang

knockknock. 🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code

vision-hw0. The 0th homework for computer vision.

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

pytorch-mobilenet-v3. MobileNetV3 in pytorch and ImageNet pretrained models

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

labs. Lab skeleton code for students

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

kill-the-bits. Code for: "And the bit goes down: Revisiting the quantization of neural networks"

quantized_distillation. Implements quantized distillation. Code for our paper "Model compression via distillation and quantization"

Teacher-Assistant-Knowledge-Distillation. Using Teacher Assistants to Improve Knowledge Distillation: https://arxiv.org/pdf/1902.03393.pdf

EfficientNet-PyTorch. A PyTorch implementation of EfficientNet

GSCNN. Gated-Shape CNN for Semantic Segmentation (ICCV 2019)

FCOS. FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

sparse_learning. Sparse learning library and sparse momentum resources.

fastai_pruning. Implementation of pruning techniques in fastai

BinaryNet. Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

convNet.pytorch. ConvNet training using pytorch

quantized.pytorch. Python

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

course-v3. The 3rd edition of course.fast.ai

pyrobot. PyRobot: An Open Source Robotics Research Platform

pytorch-unet. Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

myia. Myia prototyping

awesome-modern-cpp. A collection of resources on modern C++

papers. Notes on the papers I've read on deep learning. Contributions welcome !

model-optimization. A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

proxylessnas. [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

mlir. "Multi-Level Intermediate Representation" Compiler Infrastructure

micronet-challenge.github.io. MicroNet Website

cs140e-win19. cs140e winter 2019 class materials.

ostep-projects. Projects for an undergraduate OS course

cs140e. CS140e without Rust is not CS140e. Sergio Benitez plz come back.

cs140e. Project for the Stanford CS140e course back in 2018, creating a mini Rust-based OS for Raspberry Pi. I developed this while following along online.

colabtools. Python libraries for Google Colaboratory

pytorch.github.io. The website for PyTorch

naacl_transfer_learning_tutorial. Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA

panopticapi. COCO 2018 Panoptic Segmentation Task API (Beta version)

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

vision. Datasets, Transforms and Models specific to Computer Vision

DetNet_pytorch. An implementation of DetNet: A Backbone network for Object Detection.

Focal-Loss. loss layer of implementation

ShuffleNet_V2_pytorch_caffe. ShuffleNet-V2 for both PyTorch and Caffe.

Shufflenet-v2-Pytorch. Perfect implement. Model shared. x0.5 (Top1:60.646) and 1.0x (Top1:69.402).

nn_builder. Build neural networks with less boilerplate code

Deep-Reinforcement-Learning-Algorithms-with-PyTorch. PyTorch implementations of deep reinforcement learning algorithms and environments

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

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

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

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

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

flair. A very simple framework for state-of-the-art Natural Language Processing (NLP)

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

mnist_png. MNIST converted to PNG format

convnet-burden. Memory consumption and FLOP count estimates for convnets

Grokking-Deep-Learning. this repository accompanies the book "Grokking Deep Learning"

ILearnMachineLearning.js. Thanks to this project I could combine my knowledge from two areas: machine learning and web development. The whole application is written in React using TypeScript and Redux, but the engine that drives it is TensorFlow.js - a modern library for training and deploying machine learning models.

Pelee. Pelee: A Real-Time Object Detection System on Mobile Devices

MultiNet. Real-time Joint Semantic Reasoning for Autonomous Driving

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

M2Det. M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

yacs. YACS -- Yet Another Configuration System