30 Amazing Machine Learning Projects for the Past Year (v.2018)

Mybridge
Mybridge for Professionals
6 min readJan 5, 2018

--

For the past year, we’ve compared nearly 8,800 open source Machine Learning projects to pick Top 30 (0.3% chance).

This is an extremely competitive list and it carefully picks the best open source Machine Learning libraries, datasets and apps published between January and December 2017. Mybridge AI evaluates the quality by considering popularity, engagement and recency. To give you an idea about the quality, the average number of Github stars is 3,558.

  • Python Projects of the Year (avg. 3,707 ⭐️): Here (0 duplicate)
  • Machine Learning Open Source Tools & Projects of the Year v.2019: Here
  • Machine Learning Articles of the Year v.2019: Here

Open source projects can be useful for data scientists. You can learn by reading the source code and build something on top of the existing projects. Give a plenty of time to play around with Machine Learning projects you may have missed for the past year.

(Click the numbers below. Credit given to the biggest contributor.)

No 1

FastText: Library for fast text representation and classification. [11786 stars on Github]. Courtesy of Facebook Research

……….. [ Muse: Multilingual Unsupervised or Supervised word Embeddings, based on Fast Text. 695 stars on Github]

No 2

Deep-photo-styletransfer: Code and data for paper “Deep Photo Style Transfer” [9747 stars on Github]. Courtesy of Fujun Luan, Ph.D. at Cornell University

No 3

The world’s simplest facial recognition api for Python and the command line [8672 stars on Github]. Courtesy of Adam Geitgey

No 4

Magenta: Music and Art Generation with Machine Intelligence [8113 stars on Github].

No 5

Sonnet: TensorFlow-based neural network library [5731 stars on Github]. Courtesy of Malcolm Reynolds at Deepmind

No 6

deeplearn.js: A hardware-accelerated machine intelligence library for the web [5462 stars on Github]. Courtesy of Nikhil Thorat at Google Brain

No 7

Fast Style Transfer in TensorFlow [4843 stars on Github]. Courtesy of Logan Engstrom at MIT

No 8

Pysc2: StarCraft II Learning Environment [3683 stars on Github]. Courtesy of Timo Ewalds at DeepMind

No 9

AirSim: Open source simulator based on Unreal Engine for autonomous vehicles from Microsoft AI & Research [3861 stars on Github]. Courtesy of Shital Shah at Microsoft

No 10

Facets: Visualizations for machine learning datasets [3371 stars on Github]. Courtesy of Google Brain

No 11

Style2Paints: AI colorization of images [3310 stars on Github].

No 12

Tensor2Tensor: A library for generalized sequence to sequence models — Google Research [3087 stars on Github]. Courtesy of Ryan Sepassi at Google Brain

No 13

Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more) [2847 stars on Github]. Courtesy of Jun-Yan Zhu, Ph.D at Berkeley

No 14

Faiss: A library for efficient similarity search and clustering of dense vectors. [2629 stars on Github]. Courtesy of Facebook Research

No 15

Fashion-mnist: A MNIST-like fashion product database [2780 stars on Github]. Courtesy of Han Xiao, Research Scientist Zalando Tech

No 16

ParlAI: A framework for training and evaluating AI models on a variety of openly available dialog datasets [2578 stars on Github]. Courtesy of Alexander Miller at Facebook Research

No 17

Fairseq: Facebook AI Research Sequence-to-Sequence Toolkit [2571 stars on Github].

No 18

Pyro: Deep universal probabilistic programming with Python and PyTorch [2387 stars on Github]. Courtesy of Uber AI Labs

No 19

iGAN: Interactive Image Generation powered by GAN [2369 stars on Github].

No 20

Deep-image-prior: Image restoration with neural networks but without learning [2188 stars on Github]. Courtesy of Dmitry Ulyanov, Ph.D at Skoltech

No 21

Face_classification: Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV. [1967 stars on Github].

No 22

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition using DeepMind’s WaveNet and tensorflow [1961 stars on Github]. Courtesy of Namju Kim at Kakao Brain

No 23

StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation [1954 stars on Github]. Courtesy of Yunjey Choi at Korea University

No 24

Ml-agents: Unity Machine Learning Agents [1658 stars on Github]. Courtesy of Arthur Juliani, Deep Learning at Unity3D

No 25

DeepVideoAnalytics: A distributed visual search and visual data analytics platform [1494 stars on Github]. Courtesy of Akshay Bhat, Ph.D at Cornell University

No 26

OpenNMT: Open-Source Neural Machine Translation in Torch [1490 stars on Github].

No 27

Pix2pixHD: Synthesizing and manipulating 2048x1024 images with conditional GANs [1283 stars on Github]. Courtesy of Ming-Yu Liu at AI Research Scientist at Nvidia

No 28

Horovod: Distributed training framework for TensorFlow. [1188 stars on Github]. Courtesy of Uber Engineering

No 29

AI-Blocks: A powerful and intuitive WYSIWYG interface that allows anyone to create Machine Learning models [899 stars on Github].

No 30

Deep neural networks for voice conversion (voice style transfer) in Tensorflow [845 stars on Github]. Courtesy of Dabi Ahn, AI Research at Kakao Brain

That’s it for Machine Learning Open Source of the Year. Visit our publication to find top posts for more programming skills.

Recommend & share..

--

--