AI Top Rated Open Source Projects in 2020

Fork me on GitHub

Are you ready to start your new AI project?
looking for the best open source libraries, frameworks, SDKs to use?
In the below map, you’ll find a curated list of the most advanced and innovative open source projects to be considered in you data science initiative for 2020.

Drop a comment below or submit a pull-request here, if you believe a relevant project was left behind.

Best Data Science Open Source Tools

Classic Machine Learning

SciKit Learn – Machine Learning in Python GH Stars

Monster

XGBoost – Scalable and Flexible Gradient Boosting GH Stars

Accord.NET – Machine learning, computer vision, statistics for .NET GH Stars

Deep Learning

TensorFlow – An end-to-end open source machine learning platform GH Stars

Sonnet – TensorFlow-based neural network library GH Stars

PyTorch – Tensors and Dynamic neural networks in Python with strong GPU acceleration GH Stars

Start your future with a Data Analysis Certificate.

MXNet – Lightweight, Portable, Flexible Distributed/Mobile Deep Learning GH Stars

DL4j – Open-source, distributed, deep learning library for the JVM GH Stars

Reinforment Learning

Gym – A toolkit for developing and comparing reinforcement learning algorithms GH Stars

Dopamine – a research framework for fast prototyping of reinforcement learning algorithms. GH Stars

ReAgent – A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.) GH Stars

Start your future with a Data Analysis Certificate.

Tensorlayer – Deep Learning and Reinforcement Learning Library for Scientists GH Stars

Natural Language Processing

BERT – A new method of pre-training language representationsGH Stars

Transformers – State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch GH Stars

AllenNLP – An open-source NLP research library, built on PyTorch. GH Stars

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

Start your future with a Data Science Certificate.

spaCy – Industrial-Strength Natural Language Processing GH Stars

fastText – Library for efficient text classification and representation learning GH Stars

Speech Recognition

Kaldi – Kaldi is a toolkit for speech recognition GH Stars

DeepSpeech – A TensorFlow implementation of Baidu’s DeepSpeech architecture GH Stars

wav2letter – Facebook AI Research’s Automatic Speech Recognition Toolkit GH Stars

Start your future with a Data Science Certificate.

Computer Vision

YOLO – Real-Time Object Detection GH Stars

OpenCV – undefined GH Stars

Detectron2 – Detectron2 is FAIR’s next-generation research platform for object detection. GH Stars

OpenPose – Real-time multi-person keypoint detection library for body, face, hands, and foot estimation GH Stars

facenet – Face recognition using Tensorflow GH Stars

Online computer science courses to jumpstart your future.

Distributed Training

Spark MLlib – Apache Spark’s scalable machine learning library. GH Stars

Mahout – For Creating Scalable Performant Machine Learning Applications GH Stars

Horovod – Uber’s Open Source Distributed Deep Learning Framework for TensorFlow GH Stars

Dask – Advanced parallelism for analytics, enabling performance at scale for the tools you love GH Stars

Ray – A fast and simple framework for building and running distributed applications GH Stars

AutoML

TPOT – A Python Automated Machine Learning. GH Stars

AutoKeras – Accessible AutoML for deep learning. GH Stars

Featuretools – An open source python framework for automated feature engineering GH Stars

NNI – An open source AutoML toolkit for neural nets hyper-parameter tuning. GH Stars

AdaNet – Fast and flexible AutoML with learning guarantees GH Stars

IDEs

Jupyter – Interactive computing across dozens of programming languages. GH Stars

Spyder – The Scientific Python Development Environment GH Stars

Zeppelin – Web-based notebook that enables data-driven, interactive data analytics. GH Stars

Platforms

H2O – Fast Scalable Machine Learning For Smarter Applications GH Stars

MLflow – An open source platform for the machine learning lifecycle GH Stars

Kubeflow – The Machine Learning Toolkit for Kubernetes GH Stars

Scoring

ONNX – The open ecosystem for interchangeable AI models. GH Stars

Seldon – Open source machine learning deployment GH Stars


About the map

The map had been generated using a javascript based visualization library – D3js (treemap visualization) against a json file.

Content can be forked here: https://github.com/haggaishachar/techmap

2 comments

  1. Career skills to jumpstart your future.
  2. 黃梓翔

    Hello Mr. Shachar:

    My name is Sean Huang. I work at a Taiwanese research institution. Can I use your picture “best data science open source tools” for our employee magazine which is aimed for sharing the AI domain knowledge.

    Thank you!

    Best Regards,
    Sean Huang

Leave a Reply

Your email address will not be published. Required fields are marked *