Forrest Iandola

AdcSR. (CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]

CCSR. [TIP2026] Official codes of CCSRv2 and CCSRv1: Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution

PiSA-SR. [CVPR 2025] Official code repository for "Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach"

Isaac-GR00T. NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

python-pathfinding. Implementation of common pathfinding algorithms

obj2mjcf. A CLI for processing composite Wavefront OBJ files for use in MuJoCo.

furniture_sim. MuJoCo simulation for common furnitures

RoboVerse. RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

vlfm. The repository provides code associated with the paper VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation (ICRA 2024)

pirlnav. Code for training embodied agents using IL and RL finetuning at scale for ObjectNav

open-pi-zero. Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

openpi. Python

mm-fit. MM-Fit - Getting Started

HAR-for-fitness-data. Human Activity Recognition for workout exercises

tweaks. Patch series for software I use a lot

python-OBD. OBD-II serial module for reading engine data

FlashGS. C++

buck2. Build system, successor to Buck

MobileLLM. MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

stream-cuda. A CUDA implementation of the STREAM benchmark.

gsplat. CUDA accelerated rasterization of gaussian splatting

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2

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

mamba. Mamba SSM architecture

EfficientSAM. EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

nos. ⚡️ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW.

FP8-quantization. Python

smoothquant. [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

demucs. Code for the paper Hybrid Spectrogram and Waveform Source Separation

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

ActivityNet. This repository is intended to host tools and demos for ActivityNet

flores. Facebook Low Resource (FLoRes) MT Benchmark

davis-interactive. Package to evaluate interactive segmentation with scribbles at DAVIS dataset.

davis2017-evaluation. Evaluation Framework for DAVIS 2017 Semi-supervised and Unsupervised used in the DAVIS Challenges

training. Reference implementations of training benchmarks

aesthetic-predictor. A linear estimator on top of clip to predict the aesthetic quality of pictures

point-e. Point cloud diffusion for 3D model synthesis

ChatGPT. Reverse engineered ChatGPT API

mmdeploy. OpenMMLab Model Deployment Framework

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Applied-Deep-Learning. Applied Deep Learning Course

VRT. VRT: A Video Restoration Transformer (official repository)

PantoMatrix. PantoMatrix: Generating Face and Body Animation from Speech

HA2G. [CVPR 2022] Code for "Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation"

HumanBehaviorAnimation. Python

SEEG. Code for SEEG: Semantic Energized Co-speech Gesture Generation

Bi-SimCut. Code for NAACL 2022 main conference paper "Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation"

litepose. [CVPR'22] Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation

Diff-DALLE. Python

ZenNAS. Python

MobileDLFrameworksBenchmark. Python

EntropyHeatCapacity. Python

python-chromedriver-autoinstaller. The chromedriver auto installer for distribution.

FOX-NAS. FOX-NAS: Fast, On-device and Explainable NeuralArchitecture Search

OpenShadingLanguage. Advanced shading language for production GI renderers

cutlass. CUDA Templates and Python DSLs for High-Performance Linear Algebra

fastformers. FastFormers - highly efficient transformer models for NLU

Gpufit. GPU-accelerated Levenberg-Marquardt curve fitting in CUDA

text-extensions-for-pandas. Natural language processing support for Pandas dataframes.

matplotlib-cpp. Extremely simple yet powerful header-only C++ plotting library built on the popular matplotlib

argparse. Argument Parser for Modern C++

prezsim. 2020 Presidential Election Simulation

temperature_scaling. A simple way to calibrate your neural network.

PyTorch_YOLOv4. PyTorch implementation of YOLOv4

Flux.jl. Relax! Flux is the ML library that doesn't make you tensor

angular-ngx-charts-demo. Data visualizations with Angular7 and NGX Charts

mongo-wrapper. tiny wrapper around the native mongodb driver

justgage. JustGage is a handy JavaScript plugin for generating and animating nice & clean dashboard gauges. It is based on Raphaël library for vector drawing.

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.

pulse. PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

TensorRT. NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

inequity-release. Code to accompany 2019 paper.

experiment-impact-tracker. Python

ELECTRA-Pytorch. This is kinda convoluted re-implementation of ELECTRA

electra_pytorch. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

fgvcx-icassava. Cassava disease prediction for the FGVCx competition of CVPR

adahessian. ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning

Pretrained-Language-Model. Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

CNN_sentence. CNNs for sentence classification

automl. Google Brain AutoML

google-research. Google Research

electra. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

torchprofile. Count the MACs / FLOPs of PyTorch models

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.

redshift. Redshift adjusts the color temperature of your screen according to your surroundings. This may help your eyes hurt less if you are working in front of the screen at night.

transformer-on-diet. Code repo for "Transformer on a Diet" paper

naacl-pubs. Place to collect updated documents needed by the NAACL publications co-chairs.

naacl-pubs. Place to collect updated documents needed by the NAACL publications co-chairs.

fast-LayerNorm-TF. Efficient layer normalization GPU kernel for Tensorflow

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

YouTokenToMe. Unsupervised text tokenizer focused on computational efficiency

squeezenas. Python

CPD. a high performance system for customized-precision distributed deep learning

mt-dnn. Multi-Task Deep Neural Networks for Natural Language Understanding

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

albert. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

torchprof. PyTorch layer-by-layer model profiler

PyHessian. PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

flops-counter.pytorch. Flops counter for neural networks in pytorch framework

jetson_easy. 🔩 Automatically script to setup and configure your NVIDIA Jetson [Nano, Xavier, TX2i, TX2, TX1, TK1] . This script run different modules to update, fix and patch the kernel, install ROS and other...

jetson_stats. 📊 Simple package for monitoring and control your NVIDIA Jetson [Orin, Xavier, Nano, TX] series

jetson_nano. This repository is a collection of scripts/programs I use to set up the software development environment on my Jetson Nano, TX2, and Xavier NX.

torch2trt. An easy to use PyTorch to TensorRT converter

pytorch-examples. Simple examples to introduce PyTorch

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/.

antialiased-cnns. pip install antialiased-cnns to improve stability and accuracy

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

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

slimmable_networks. Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019

text-proc. Scripts for Text Processing

Realistic-Neural-Talking-Head-Models. My implementation of Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (Egor Zakharov et al.).

texar-pytorch. Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/

bookcorpus. Crawl BookCorpus

wikiextractor. A tool for extracting plain text from Wikipedia dumps

nlp-datasets. Alphabetical list of free/public domain datasets with text data for use in Natural Language Processing (NLP)

gluon-nlp. NLP made easy

mobile-vision. Mobile vision models and code

transformer-xl. Training Transformer-XL on 128 GPUs

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

xlnet. XLNet: Generalized Autoregressive Pretraining for Language Understanding

transformer-xl. Python

cuBERT. Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL

d2l-en. Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

ml-glossary. Machine learning glossary

BerryNet. Deep learning gateway on Raspberry Pi and other edge devices

clang-tidy-misra. MISRA C:2012 and MISRA C++:2008 compliance checkers for clang-tidy

VINS-Mobile-Android. C++

VINS-Fusion. An optimization-based multi-sensor state estimator

limo. Lidar-Monocular Visual Odometry

LKVOLearner. Learning Depth from Monocular Videos using Direct Methods, CVPR 2018

DeepVO-pytorch. PyTorch Implementation of DeepVO

mace. MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

AI-Chip. A list of ICs and IPs for AI, Machine Learning and Deep Learning.

sweethome3d. This repository was imported using cvs2git tool

light_head_rcnn. Light-Head R-CNN

UT-Dallas-CS-6301-CNNs. Deep Learning Class

dvc. 🦉 Data Versioning and ML Experiments

dvc.org. 📖 DVC documentation website

consortium. Process Information for the Dat Protocol Working Group (Notes, Agenda, Members)

DORN. Jupyter Notebook

channel-pruning. Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

ffld. Charles Dubout's Accelerated Deformable Part Model

YOLO-CoreML-MPSNNGraph. Tiny YOLO for iOS implemented using CoreML but also using the new MPS graph API.

imgclsmob. Sandbox for training deep learning networks

deep-residual-networks. Deep Residual Learning for Image Recognition

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

training_policies. Issues related to MLPerf™ training policies, including rules and suggested changes

dlcookbook-dlbs. Deep Learning Benchmarking Suite

CoreMLZoo. A few models converted from caffe to CoreMLs format.

SqueezeNext.

Awesome-CoreML-Models. Largest list of models for Core ML (for iOS 11+)

bdd100k. This repo has been moved to https://github.com/bdd100k/bdd100k permanently.

intrinsic-dimension. Jupyter Notebook

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

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

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

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

caffe64. No dependency caffe replacement

gloo. Collective communications library with various primitives for multi-machine training.

SqueezeSeg. Implementation of SqueezeSeg, convolutional neural networks for LiDAR point clout segmentation

carnd. A repo to throw my self driving carnd projects into.

ComputeLibrary. The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

Caffe-HRT. Heterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.

gemmlowp. Low-precision matrix multiplication

teachable-machine-v1. Explore how machine learning works, live in the browser. No coding required.

encore.ai. Generate new lyrics in the style of any artist using LSTMs and TensorFlow.

caffe-jacinto. This repository has moved. The new link can be obtained from https://github.com/TexasInstruments/jacinto-ai-devkit

ELL. Embedded Learning Library

really-awesome-semantic-segmentation. A list of papers on Semantic Segmentation.

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

unrealcv. UnrealCV: Connecting Computer Vision to Unreal Engine

neural-style. Torch implementation of neural style algorithm

Amodal3Det. Jupyter Notebook

Caffe-ShuffleNet. This is re-implementation of "ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices"

squeezenet. Implementation of a SqueezeNet [1] -type encoder and decoder for Semantic Segmentation in Tensorflow.

SqueezeNet_v1.2. Top-1 Acc=61.0% on ImageNet, without any sacrificing compared with SqueezeNet v1.1.

ResNet. Reproduce ResNet-v2(Identity Mappings in Deep Residual Networks) with MXNet

squeezenet-keras. SqueezeNet Keras demo

FalsifCPSML. Compositional falsification framework for cyber-pysical systems with machine learning components

slurm-env-config. slurm-env-config writes a slurm conf file from environment variables

config-slurm.

librealsense. RealSense SDK

mxnet. Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

clSpMV. The repository of the clSpMV code.

greenthumb. Racket

squeezeDet. A tensorflow implementation for SqueezeDet, a convolutional neural network for object detection.

neural-enhance. Super Resolution for images using deep learning.

pyart. The Python-ARM Radar Toolkit. A data model driven interactive toolkit for working with weather radar data.

zynqnet. Master Thesis "ZynqNet: An FPGA-Accelerated Embedded Convolutional Neural Network"

cnn-benchmarks. Benchmarks for popular CNN models

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

caffe2neon. Tools to convert Caffe models to neon's serialization format

pcl. Point Cloud Library (PCL)

colorization. Automatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.

latte. CMU 15-418/618 Final Project: Implementing Fully Convolutional Network using Halide and evaluate against Caffe version

research. dataset and code for 2016 paper "Learning a Driving Simulator"

ROCm. AMD ROCm™ Software - GitHub Home

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

darknet. Convolutional Neural Networks