Skip to content

📝 References list for machine learning and deep learning in computer vision.

Notifications You must be signed in to change notification settings

mheriyanto/machine-learning-in-computer-vision

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Machine Learning and Deep Learning in Computer Vision

Data is the new oil? No: Data is the new soil. ~ David McCandless

Awesome contributions welcome GitHub contributors GitHub last commit HitCount LinkedIn

⭐ - Recommendations for Beginners.

Awesome Lists

Artificial Intelligence

Machine Learning

Deep Learning

Computer Vision

Production

Compilers

  • Awesome machine learning for compilers and program optimisation: zwang4 GitHub stars

Concepts

Mathematics Concepts

  • ProofWiki (proofwiki.org): Web
  • Book of Proof (Richard Hammack, 2018, 3rd Ed.): Book | Web
  • Book of Proofs (bookofproofs.org): Web

Machine Learning Concepts

  • Pengenalan Pembelajaran Mesin dan Deep Learning (J.W.G. Putra, 2019): Book | GitHub | Web
  • Machine Learning Probabilistic Prespective (K.P. Murphy, 2012. The MIT Press): Book | GitHubGitHub stars | Solution | Web
  • Pattern Recognition and Machine Learning (C.M. Bishop. 2006. Springer): Book | GitHubGitHub stars | Web
  • Mathematics for Machine Learning (M.P. Deisenroth. 2020. Cambridge University Press) Web | Book update. Book printed

Deep Learning Concepts

  • Principles of Artificial Neural Networks (Daniel Graupe, 2013): Book
  • Principles of Neurocomputing for Science and Engineering (Fredric M. Ham, 2001): Book
  • Neural Networks and Deep Learning (M. Nielsen, 2018): Book | GitHubGitHub stars | Web
  • Neural Networks and Deep Learning (C.C. Aggarwal, 2018. Springer): Book | Web | Slide
  • Deep Learning (I. Goodfellow, Y. Bengio, & A. Courville. 2016. The MIT Press): Book | GitHubGitHub stars | Web
  • Math and Architectures of Deep Learning (K. Chaudhury . 2020. MEAP): Book

Computer Vision Concepts

  • Computer Vision: Models, Learning, and Inference (Simon J.D. Prince 2012. Cambridge University Pres): Web | Book | GitHubGihttps://deeplearning.mit.edu/tHub stars | Matlab Code
  • Computer Vision: Algorithms and Application (R. Szeliski 2010. Springer): Book | GitHubGitHub stars | Web

All with Python

Basic Python Books

  • CheatSheet > Comprehensive Python CheatsheetGitHub stars
  • Python 3 Object-oriented Programming (D. Phillips. 2015. O'Reilly Media): Book | GitHubGitHub stars | Web
  • Learning Python Design Patterns (G. Zlobin. 2013. Packt): Book | GitHubGitHub stars
  • Mastering Python Design Patterns (S. Kasampalis & K. Ayeva. 2018. Packt): Book | GitHubGitHub stars
  • Clean Code in Python (M. Anaya. 2018. Packt): Book | GitHubGitHub stars
  • A collection of design patterns/idioms in Python (Sakis Kasampalis. GitHub): GitHubGitHub stars

Machine Learning with Python

  • Introduction to Machine Learning with Python (A.C. Muler & S. Guido. 2017. O'Reilly Media): Book | GitHubGitHub stars | Web
  • Practical Machine Learning with Python (D. Sarkar, R. Bali, and T. Sharma. 2018. Apress): Book | GitHubGitHub stars
  • Machine Learning Applications Using Python (P. Mathur. 2019. Apress): Book | GitHubGitHub stars

Deep Learning with Python

  • Deep Learning with Applications Using Python (N.K. Manaswi, 2018. Apress): Book | GitHubGitHub stars
  • Dive into Deep Learning - NumPy/MXNet and PyTorch implementations (Aston Zhang, 2020): Book | GitHubGitHub stars
    • Dive into Deep Learning Compiler (Aston Zhang, 2020): Book | GitHubGitHub stars
  • Deep Learning with PyTorch (Eli Stevens, 2020. MEAP): Book

Computer Vision with Python

  • Computer Vision with Python 3 (S. Kapur, 2017. Packt): Book | GitHubGitHub stars
  • Programming Computer Vision with Python: Tools And Algorithms For Analyzing Images (Jan Erik Solem, 2012. O'Reilly): Book
  • Modern Computer Vision with PyTorch (V Kishore Ayyadevara, 2020. Packt): Book | GitHub

All with C++

Basic C++ Books

Machine Learning with C++

  • Hands-On Machine Learning with C++ (K. Kolodiazhnyi, 2020-05. Packt): Book | GitHubGitHub stars

Deep Learning with C++

  • C++ Implementation of PyTorch Tutorials for Everyone: GitHubGitHub stars
  • LibtorchTutorials: This is a code repository for pytorch c++ (or libtorch) tutorial. GitHub
    • LibtorchDetection: C++ trainable detection library based on libtorch (or pytorch c++). Yolov4 tiny provided now.
    • LibtorchSegmentation: A c++ trainable semantic segmentation library based on libtorch (pytorch c++). Backbone: VGG, ResNet, ResNext. Architecture: FPN, U-Net, PAN, LinkNet, PSPNet, DeepLab-V3, DeepLab-V3+ by now.

Image Processing & Computer Vision with C++

  • Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library: Book | GitHub
  • The CImg Library is a small and open-source C++ toolkit for image processing: Web

ML Design Patterns & Clean Code Books

  • Machine Learning Design Patterns (V. Lakshmanan, S. Robinson, M. Munn. 2020. O'Reilly): Book | GitHubGitHub stars
  • Clean Machine Learning Code (M. Taifi, 2020. Leanpub): Book | Course

ML DevOps Books

  • Building Machine Learning Pipelines: Automating Model Life Cycles with TensorFlow (Hannes Hapke, 2020. O'Reilly): Book
  • Introducing MLOps: How to Scale Machine Learning in the Enterprise (Mark Treveil. 2020. O'Reilly): Book
  • Designing Machine Learning Systems (C. Huyen, 2022. O'Reilly): Book | GitHubGitHub stars

Deep Learning Frameworks

  • Deep Learning with Keras (S. Pal & A. Gulli, 2017. Packt): Book and CodeGitHub stars

TensorFlow Frameworks

  • Project Templates

  • Awesome Lists

  • TensorFlow Books: jtoy/awesome-tensorflow#books | Amin-Tgz/awesome-tensorflow-2#books

    • Python Machine Learning - Second Edition: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow (Sebastian Raschka, 2017. Packt): Book | GitHub
    • Deep Learning with Python (François Chollet, 2017. Manning): Book | GitHub
    • Deep Learning with TensorFlow (G. Zaccone & Md.R. Karim, 2018. Packt): Book, Code, and GitHubGitHub stars
    • Deep Learning with TensorFlow 2 and Keras: Regression, ConvNets, GANs, RNNs, NLP, and more with TensorFlow 2 and the Keras API, 2nd Edition (Antonio Gulli, 2019. Packt): Book | GitHub
    • Hands-On Computer Vision with TensorFlow 2: Leverage deep learning to create powerful image processing apps with TensorFlow 2.0 and Keras (Benjamin Planche, 2019. Packt): Book | GitHub
    • Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (Aurélien Géron, 2019. O'Reilly): Book | GitHub
    • Practical Deep Learning for Cloud, Mobile, and Edge: Real-World AI & Computer-Vision Projects Using Python, Keras & TensorFlow (Anirudh Koul, 2019. O'Reilly): Book | GitHub
    • Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (Aurélien Géron, 2019. O'Reilly). Book | GitHub
  • TensorFlow Lite Books: margaretmz/awesome-tensorflow-lite#books

    • TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers (Pete Warden, 2020-01. O'Reilly Media): Book
    • Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter: Build scalable real-world projects to implement end-to-end neural networks on Android and iOS (Anubhav Singh, Rimjhim Bhadani, 2020. Packt): Book

PyTorch Frameworks

Network Programming

  • Foundations of Python Network Programming (Brandon Rhodes. 2014. Apress): Book | GitHub GitHub stars
  • C++ Network Programming, Volume I: Mastering Complexity with ACE and Patterns (Douglas Schmidt. 2001. Addison-Wesley Professional): Book
  • C++ Network Programming, Volume 2: Systematic Reuse with ACE and Frameworks (Douglas Schmidt. 2002. Addison-Wesley Professional): Book

Courses

Machine Learning

  • Belajar Machine Learning Lengkap Dari Nol Banget sampai Practical - WiraD.K. Putra (2020): YouTube | GitHub
  • Standford Machine Learning - Standford by Andrew Ng (2008): YoutTube
  • Caltech Machine Learning - Caltech by Yaser Abu-Mostafa (2012-2014): Web
  • Neural networks - University De Sherbrooke by Hugo Larochelle (2013): YouTube | Web

Deep Learning

  • Deep Learning Drizzle - Mario (2021): Website | GitHub GitHub stars
  • Carnegie Mellon University Deep Learning - CMU: YouTube | Web
  • Deeplearning.ai Neural Networks and Deep Learning - Deeplearning.ai by Andrew Ng in YouTube (2010-2014): YouTube
  • Standford Neural Networks and Deep Learning - Standford by Fei-Fei Li: YouTube: 2017
  • MIT Deep Learning - MIT by Lex Fridman: GitHubGitHub stars | YouTube
  • Stanford Deep Learning - Stanford by Andrew Ng: Homepage | Web | Coursera | GitHubGitHub stars
  • Deep Neural Networks with PyTorch - IBM by Joseph Santarcangelo: coursera
  • Deep Learning with PyTorch - by sentdex: YouTube
  • Computer Vision - Univ. Central Florida by Mubarak Shah YouTube

TinyML

  • CS249r: Tiny Machine Learning (TinyML) - Harvard by Vijay Janapa Reddi: sites.google.com | YouTube | edx| GitHub
  • Introduction to Embedded Machine Learning - Edge Impulse by Shawn Hymel: coursera
  • Embedded and Distributed AI - Jonkoping University, Sweden by Beril Sirmacek: YouTube

MLOps

  • Machine Learning Engineering for Production MLOps - by Andrew Ng (2021): Coursera

Research Groups

Universities

Communities

  • Q-engineering: Computer vision, Machine learning, Applied mathematics. GitHub
  • HUAWEI Noah's Ark Lab: Working with and contributing to the open source community in data mining, artificial intelligence, and related fields.
  • MIT HAN Lab: Accelerating Deep Learning Computing. Website
    • Tiny Machine Learning: Our projects are covered by: MIT News, WIRED, Morning Brew, Stacey on IoT, Analytics Insight, Techable. Web.
    • once-for-all: [ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment.
    • proxylessnas: [ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware.
  • TinyML - Harvard University
    • tinyMLx - colabs: This repository holds the Google Colabs for the EdX TinyML Specialization.
    • tinyMLx - courseware: In this repository you will find TinyML course syllabi, assignments/labs, code walkthroughs, links to student projects, and lecture videos (where applicable).
    • arduino-library: Harvard_TinyMLx Arduino Library.
  • NVIDIA Corporation
    • TRTorch: PyTorch/TorchScript compiler for NVIDIA GPUs using TensorRT.
    • apex: A PyTorch Extension: Tools for easy mixed precision and distributed training in PyTorch.
    • DeepLearningExamples: provides State-of-the-Art Deep Learning examples that are easy to train and deploy, achieving the best reproducible accuracy and performance with NVIDIA CUDA-X software stack running on NVIDIA Volta, Turing and Ampere GPUs.
    • libcudacxx: The C++ Standard Library for your entire system.
  • NVIDIA-AI-IOT
  • OpenMMLab: mmcv - OpenMMLab Computer Vision Foundation.
    • mmclassification: OpenMMLab Image Classification Toolbox and Benchmark
    • mmdetection: OpenMMLab Detection Toolbox and Benchmark.
    • mmsegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark.
    • mmtracking: OpenMMLab Video Perception Toolbox. It supports Single Object Tracking (SOT), Multiple Object Tracking (MOT), Video Object Detection (VID) with a unified framework.
    • mmdetection3d: OpenMMLab's next-generation platform for general 3D object detection.
  • Open Neural Network Exchange: ONNX is an open ecosystem for interoperable AI models. It's a community project: we welcome your contributions!
    • onnx: Open standard for machine learning interoperability.
    • onnx-tutorial: Tutorials for creating and using ONNX models.
    • onnx-models: A collection of pre-trained, state-of-the-art models in the ONNX format.
    • tensorflow-onnx: Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX.
    • onnx-tensorrt: ONNX-TensorRT: TensorRT backend for ONNX.
  • Cloud-CV: Building platforms for reproducible AI research.
    • EvalAI: Evaluating state of the art in AI.
    • Fabrik: Collaboratively build, visualize, and design neural nets in browser.
    • Origami: Origami: Artificial Intelligence as a Service.
  • Iterative: Developer Tools for Machine Learning.
    • dvc: Data Version Control | Git for Data & Models | ML Experiments Management.
    • cml: Continuous Machine Learning | CI/CD for ML.
  • Machine Learning Tooling - Open-source machine learning tooling to boost your productivity
    • ml-workspace: All-in-one web-based IDE specialized for machine learning and data science.
    • ml-hub: Multi-user development platform for machine learning teams. Simple to setup within minutes.
    • best-of-ml-python: A ranked list of awesome machine learning Python libraries.
    • best-of-web-python: A ranked list of awesome python libraries for web development.
    • opyrator: Turns your machine learning code into microservices with web API, interactive GUI, and more.
  • Megvii - BaseDetection.
    • YOLOX: is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported.
    • cvpods: All-in-one Toolbox for Computer Vision Research.
  • AMAI GmbH: AI-Expert-Roadmap: Roadmap to becoming an Artificial Intelligence Expert in 2021.
  • Machine Learning Tokyo: AI_Curriculum: Open Deep Learning and Reinforcement Learning lectures from top Universities like Stanford, MIT, UC Berkeley.
  • Distributed (Deep) Machine Learning Community: xgboost
  • EthicalML: The Institute for Ethical Machine Learning - The Institute for Ethical Machine Learning is a think-tank that brings together with technology leaders, policymakers & academics to develop standards for ML.
  • Hugging Face: The AI community building the future. Website
    • accelerate: A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision.
    • knockknock: Knock Knock: Get notified when your training ends with only two additional lines of code.
    • datasets: The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools.
    • transformers: Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

Corporations

Ph.D. in Machine Learning

Products

AI Start-Up in Indonesia

Datasets

cvpapers.com | wikipedia.org | datasetlist.com | deeplearning.net | datahub.io | towardsai.net | medium-towards-artificial-intelligence

Vehicle Classification

  • Vehicle image database - Universidad Politécnica de Madrid (UPM) by J. Arróspide (2012) - 3425 images of vehicle rears: Web

Object Detection & Recognition

  • CIFAR10 [10] - University of Toronto by Alex Krizhevsky (2009): Raw (10 classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck) | pdf
  • PASCAL VOC [20] - M. Everingham (2012): Raw (20 classes: person: person; animal:bird, cat, cow, dog, horse, sheep; vehicle: aeroplane, bicycle, boat, bus, car, motorbike, train; indoor: bottle, chair, dining table, potted plant, sofa, tv/monitor) | pdf
  • COCO [80] - COCO Consortium by Tsung-Yi Lin, et. al. (2015): Web | Download (80 classes: person & accessory, animal, vehicle, aoutdoor objects, sports, kitchenware, food, furniture, appliance, electronics, and indoor objects) | pdf
  • CIFAR100 [100] - University of Toronto by Alex Krizhevsky (2009): Raw (100 classes: aquatic mammals: beaver, dolphin, otter, seal, whale; fish: aquarium fish, flatfish, ray, shark, trout, flowers: orchids, poppies, roses, sunflowers, tulips; food containers: bottles, bowls, cans, cups, plates; fruit and vegetables: apples, mushrooms, oranges, pears, sweet peppers; household electrical devices: clock, computer keyboard, lamp, telephone, television; household furniture: bed, chair, couch, table, wardrobe; insects: bee, beetle, butterfly, caterpillar, cockroach; large carnivores: bear, leopard, lion, tiger, wolf; large man-made outdoor things: bridge, castle, house, road, skyscraper; large natural outdoor scenes: cloud, forest, mountain, plain, sea; large omnivores and herbivores: camel, cattle, chimpanzee, elephant, kangaroo; medium-sized mammals: fox, porcupine, possum, raccoon, skunk; non-insect invertebrates: crab, lobster, snail, spider, worm; people: baby, boy, girl, man, woman; reptiles: crocodile, dinosaur, lizard, snake, turtle; small mammals: hamster, mouse, rabbit, shrew, squirrel; trees: maple, oak, palm, pine, willow; vehicles 1: bicycle, bus, motorcycle, pickup truck, train; vehicles 2: lawn-mower, rocket, streetcar, tank, tractor) | pdf
  • ImageNet [10,000] Stanford University by Olga Russakovsky (2012) - Raw | pdf

Object Tracking

  • KITTI [2]: Raw(2 classes: car & pedestrian) | pdf
  • LaSOT [85]: A High-quality Large-scale Single Object TrackingBenchmark - Stony Brook University by Heng Fan (2020): Raw (85 classes) | pdf
  • MOT16: A Benchmark for Multi-Object Tracking - Univ. of Adelaide by A. Milan, et. al. (2016)]: Raw | pdf
  • TAO [833]: A Large-Scale Benchmark for Tracking Any Object - Carnegie Mellon University by Achal Dave (2020): Raw (833 classes) | pdf

Monocular 3D Object Detection

  • KITTI Dataset - University of Tübingen by Andreas Geiger (2012): Raw | Object 2D | Object 3D | Bird's Eye View (8 classes: car, van, truck, pedestrian, person_sitting, cyclist, tram, and misc or don’t care)
  • Boxy Dataset - bosch-ai by Karsten Behrendt (2019): Web | 2D Box | 3D Box | Realtime | Paper (1 classes: freeways {passenger cars, trucks, campers, boats, car carriers, construction equipment, and motorcycles}, heavy traffic, traffic jams)
  • nuScenes - nuTonomy by Holger Caesar (2019-03) The nuScenes dataset is a large-scale autonomous driving dataset: Link | Toolbox | Paper (23 classes | 19 detection: animal, debris, pushable, bicycle, ambulance, police, barrier, bicycle, bus, car, construction vehicle, motorcycle, pedestrian, personal mobility, stroller, wheelchair, traffic cone, trailer, truck)
  • Cityscapes3D - Mercedes-Benz AG by Nils Gählert (2020-06), Dataset and Benchmark for Monocular 3D Object Detection: Link | Toolbox | Paper (8 classes: car, truck, bus, on rails, motorcycle, bicycle, caravan, and trailer)

Hardware

edge-ai - crespum

Edge Hardware

  • Jetson Nano Dev Board - brings accelerated AI performance to the Edge in a power-efficient and compact form factor: Website | GitHub
  • Google Coral Dev Board - is a complete toolkit to build products with local AI. Our on-device inferencing capabilities allow you to build products that are efficient, private, fast and offline: Website | GitHub
  • Intel Movidius Neural Compute Sticks - enables rapid prototyping, validation and deployment of Deep Neural Network (DNN) inference applications at the edge. : Website | GitHub
  • ARM microNPU - Processors designed to accelerate ML inference (being the first one the Ethos-U55): Website
  • Espressif ESP32-S3 - SoC similar to the well-known ESP32 with support for AI acceleration (among many other interesting differences): Website
  • RaspberryPi/Arduino/STM32 + Edge Impulse - Enabling developers to create the next generation of intelligent device solutions through embedded Machine Learning: Website | GitHub
  • OpenMV - A camera that runs with MicroPython on ARM Cortex M6/M7 and great support for computer vision algorithms. Now with support for Tensorflow Lite too.
  • JeVois - A TensorFlow-enabled camera module.
  • Maxim MAX78000 - SoC based on a Cortex-M4 that includes a CNN accelerator.
  • Beagleboard BeagleV - Open Source RISC-V-based Linux board that includes a Neural Network Engine.

Processor: The Deep Learning Compiler: A Comprehensive Survey - arXiv '20

  • Tensor Processing Unit (TPU) by Google: Wiki
  • Neural Processing Unit (NPU) by MobilePhone Company: Wiki
  • Vision Processing Unit (VPU) by NEC & Intel: Wiki
  • Intelligence Processing Unit (IPU) by Graphcore: GitHub
  • Machine Learning Unit (MLU) by Cambricon: GitHub

Deep Learning for Embedded (IOT) & Mobile Devices

Frameworks

Embedded and mobile deep learning - csarron | Awesome Mobile Machine Learning - fritzlabs | Awesome Edge Machine Learning - Bisonai | edge-ai - crespum | AI-performance - embedded-ai.bench

  • TensorFlow Lite: TensorFlow Lite is an open source deep learning framework for on-device inference.
  • The Arm's ComputeLibrary framework: ComputeLibrary is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
  • The Alibaba's MNN framework: MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba.
  • The Tencent's ncnn framework: ncnn is a high-performance neural network inference framework optimized for the mobile platform.
  • The Baidu's Paddle Lite framework: Paddle Lite is multi-platform high performance deep learning inference engine.
  • The XiaoMi's Mace framework: MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.
  • The Apple's CoreML framework: CoreML is integrate machine learning models into your app.
  • The Microsoft's ELL framework: ELL allows you to design and deploy intelligent machine-learned models onto resource constrained platforms and small single-board computers, like Raspberry Pi, Arduino, and micro:bit.
  • PyTorch Mobile: PyTorch Mobile is a new framework for helping mobile developers and machine learning engineers embed PyTorch ML models on-device.
  • dabnn - JDAI Computer Vision: dabnn is an accelerated binary neural networks inference framework for mobile platform.
  • opencv-mobile: opencv-mobile is open source computer vision library that was designed to be cross-platform. The minimal opencv for Android, iOS and ARM Linux.
  • DeepLearningKit: DeepLearningKit is Open Source Deep Learning Framework for Apple's iOS, OS X and tvOS.
  • Tengine - OAID: Tengine is a lite, high performance, modular inference engine for embedded device.
  • Bender: Bender is easily craft fast Neural Networks on iOS! Use TensorFlow models. Metal under the hood.
  • uTensor - AI inference library based on mbed (an RTOS for ARM chipsets) and TensorFlow.
  • CMSIS NN - A collection of efficient neural network kernels developed to maximize the performance and minimize the memory footprint of neural networks on Cortex-M processor cores.
  • ARM Compute Library - Set of optimized functions for image processing, computer vision, and machine learning.
  • Qualcomm Neural Processing SDK for AI - Libraries to developers run NN models on Snapdragon mobile platforms taking advantage of the CPU, GPU and/or DSP.
  • X-CUBE-AI - Toolkit for generating NN optimiezed for STM32 MCUs.
  • Neural Network on Microcontroller (NNoM) - Higher-level layer-based Neural Network library specifically for microcontrollers. Support for CMSIS-NN.
  • nncase - Open deep learning compiler stack for Kendryte K210 AI accelerator.
  • deepC - Deep learning compiler and inference framework targeted to embedded platform.
  • uTVM - MicroTVM is an open source tool to optimize tensor programs.
  • Edge Impulse - Interactive platform to generate models that can run in microcontrollers. They are also quite active on social netwoks talking about recent news on EdgeAI/TinyML.

Books

  1. Mobile Edge Artificial Intelligence [Elsevier '21]

Tools

Production

  • docker.com: build and ship apps.
  • onnx.ai: open format built to represent machine learning models.
  • mlflow.org: an open source platform for the machine learning lifecycle.
  • cortex.dev: the open source stack for machine learning engineering.
  • mlperf.org: Fair and useful benchmarks for measuring training and inference performance of ML hardware, software, and services.
  • grpc: A high performance, open source, general-purpose RPC framework.
  • gpustat: A simple command-line utility for querying and monitoring GPU status.
  • jetson-stats: Simple package for monitoring and control your NVIDIA Jetson [Xavier NX, Nano, AGX Xavier, TX1, TX2].
  • nnabla-ext-cuda: A CUDA Extension of Neural Network Libraries.

Training Model

  • DIGITS: DIGITS (the Deep Learning GPU Training System) is a webapp for training deep learning models. The currently supported frameworks are: Caffe, Torch, and Tensorflow.
  • Optuna: A hyperparameter optimization framework.
  • Determined: Deep Learning Training Platform.
  • cuDF: GPU DataFrame Library.
  • DeepSpeed: DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
  • comet.ml: track, compare, explain and optimize experiments and models.
  • dvc: Data Version Control | Git for Data & Models.
  • Weights & Biases: Experiment tracking, model and dataset versioning, hyperparameter optimization.
  • modelzoo.co: Discover open source deep learning code and pretrained models.

Visualization: Architecture

  • Netron: a viewer for neural network, deep learning and machine learning models.
  • NN-SVG: Publication-ready NN-architecture schematics.
  • ennui: Working on a drag-and-drop neural network visualizer (and more). Here's an example of a visualization for a LeNet-like architecture.
  • TensorSpace: TensorSpace is a neural network 3D visualization framework built by TensorFlow.js, Three.js and Tween.js. TensorSpace provides Layer APIs to build deep learning layers, load pre-trained models, and generate a 3D visualization in the browser. By applying TensorSpace API, it is more intuitive to visualize and understand any pre-trained models built by TensorFlow, Keras, TensorFlow.js, etc.
  • netscope: A web-based tool for visualizing and analyzing convolutional neural network architectures (or technically, any directed acyclic graph).
  • playground: Deep playground is an interactive visualization of neural networks, written in TypeScript using d3.js.
  • PerceptiLabs: a dataflow driven, visual API for TensorFlow that enables data scientists to work more efficiently with machine learning models and to gain more insight into their models.
  • conv: 3D visualization of convolutional neural network.
  • PyTorchViz: A small package to create visualizations of PyTorch execution graphs and traces.
  • PlotNeuralNet: Latex code for making neural networks diagrams.
  • ml-visuals: ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
  • traingenerator: A web app to generate template code for machine learning.
  • nni: an open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
  • nn-visualizer: Interactive 3D Neural Network Visualizer.

Dashboard

Interested Research

  • Deep Learning Models - A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks: GitHub GitHub stars
  • Hyperparameter Optimization of Machine Learning Algorithms - Implementation of hyperparameter optimization/tuning methods for machine learning & deep learning models (easy&clear): GitHub GitHub stars
  • FairMOT - A simple baseline for one-shot multi-object tracking: GitHub GitHub stars
  • Norfair - is a customizable lightweight Python library for real-time 2D object tracking: GitHub
  • Transformer: Awesome Visual-Transformer | pytorch2libtorch | Fast Transformers

Autonomous Vehicles

  • Awesome Autonomous Vehicles - manfreddiaz: GitHub GitHub stars
  • Autoware - Integrated open-source software for urban autonomous driving: Web | GitHub GitHub stars
  • CARLA Simulator - Open-source simulator for autonomous driving research: GitHub GitHub stars
  • Self-DrivingToy Car - experiencor: GitHub
  • openpilot: is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 85 supported car makes and models.

Benchmark

benchmarks.ai | dawn.cs.stanford.edu | mlperf.org | MobilePhone - ai-benchmark.com | GitHub > deep-learning-benchmark - u39kun, DeepBench - baidu-research

Create Datasets

Journals, Magazines, and People

Journals

Magazines: towardsdatascience | paperswithcode | distill | xenonstack | awesomeopensource.com | emerge-ai.com

People

Podcast

Conferences & Competitions for Image Processing & Computer Vision: guide2research.com | openaccess.thecvf.com