We compared 8,800 open source machine learning projects on GitHub and selected the Top 30 of them
Big Data Digest Works
编译：叶一、Shan LIU、Aileen
2017 was a year of machine learning applications in full bloom, with amazing ideas and projects popping up all over the place. We compared nearly 8,800 open source machine learning projects from the past year and selected the better 30 (Top 0.3%) of them to list here.
This is a highly competitive list of handpicked quality projects in the category of machine learning libraries, datasets and applications published in January-December 2017. We rated their quality by popularity, engagement, and timeliness. One statistic that will give you a visual impression of the quality of the form: the average number of GitHub stars for these projects is 3558.
开源项目对于数据科学家而言是很有意义的。你可以通过阅读源代码，在前人的基础上构建更加强大的项目。 You can have fun trying out these machine learning projects that may have missed you in the last year.
No.1 - FastText：快速文本表示/分类库
GitHub stars数: 11786个
来源：Facebook研究
链接：
https://github.com/facebookresearch/fastText
and [Muse: Multilingual unsupervised/supervised word embedding based on FastText (GitHub stars: 695) https://github.com/facebookresearch/MUSE]
No.2- Deep-photo-styletransfer：康奈尔大学 Fujun Luan 论文 Code and data for Deep Photo Style Transfer
GitHub stars数：9747个
链接：
https://github.com/luanfujun/deep-photo-styletransfer
No.3 - face recognition： The world's simplest facial recognition api for Pyhthon and the command line
Number of GitHub stars: 8672
来源：Adam Geitgey
Link:
https://github.com/ageitgey/face_recognition
No.4 - Magenta：机器智能音乐与艺术生成器
Number of GitHub stars: 8113
链接：
https://github.com/tensorflow/magenta
No.5 - Sonnet：基于 TensorFlow 的神经网络库
Number of GitHub stars: 5731
来源：DeepMind 成员 Malcolm Reynolds
链接：
https://github.com/deepmind/sonnet
No.6 - deeplearn.js：网页端硬件加速机器学习库
Number of GitHub stars: 5462
Source: Google Brain Team Nikhil Thorat
链接：
https://github.com/PAIR-code/deeplearnjs
No.7 - Fast Style Transfer： TensorFlow Fast Style Conversion
Number of GitHub stars: 4843
Source: Logan Engstrom, MIT
链接：
https://github.com/lengstrom/fast-style-transfer
No.8 - Pysc2： StarCraft II Learning Environment
Number of GitHub stars: 3683
Source: DeepMind Timo Ewalds et al.
链接：
https://github.com/deepmind/pysc2
No.9 - AirSim：微软AI和研究院出品的基于虚幻引擎的开源自动驾驶模拟器
Number of GitHub stars: 3681
Source: Microsoft's Shital Shah
链接：
https://github.com/Microsoft/AirSim
No.10 - Facets： Machine learning dataset visualization tools
Number of GitHub stars: 3371
来源：Google Brain
链接：
https://github.com/PAIR-code/facets
No.11 - Style2Paints： AI Manga Line Coloring Tool
Number of GitHub stars: 3310
链接：
https://github.com/lllyasviel/style2paints
No.12 - Tensor2Tensor：用于广义序列-序列模型的工具库
Number of GitHub stars: 3087
Source: Ryan Sepassi of Google Brain
链接：
https://github.com/tensorflow/tensor2tensor
No.13- PyTorch-based image-to-image conversion tool (e.g. horse2zebra, edges2cats, etc.)
Number of GitHub stars: 2847
Source: Dr. Junyan Zhu, UC Berkeley
链接：
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
No.14 - Faiss： A library of tools for efficient similarity retrieval and clustering with dense vectors
Number of GitHub stars: 2629
来源：Facebook
链接：
https://github.com/facebookresearch/faiss
No.15 Fashion-mnist： A MNIST-like dataset for fashion products
GitHub stars数：2780个
Source: Han Xiao of Zalando Tech
链接：
https://github.com/zalandoresearch/fashion-mnist
No.16 - ParlAI：适用于在各类公开的对话数据集上训练与评估AI模型的一个框架
Number of GitHub stars: 2578
Source: Alexander Miller of Facebook Research
链接：
https://github.com/facebookresearch/ParlAI
No.17 Fairseq：序列到序列工具包
GitHub stars数: 2571个
Source: FAIR
链接：
https://github.com/facebookresearch/fairseq
No.18 Pyro： Deep General Probabilistic Programming with Python and PyTorch
GitHub stars数: 2387个
来源：Uber AI Labs
Link:
https://github.com/uber/pyro
No.19 iGAN： GAN-based interactive image generator
Number of GitHub stars: 2369
链接：
https://github.com/junyanz/iGAN
No.20 Deep-image-prior： Image recovery using neural networks, yet without the learning process
GitHub stars数: 2188个
来源：Skoltech 的 Dmitry Ulyanov博士
链接：
https://github.com/DmitryUlyanov/deep-image-prior
No.21 Face_classification： Real-time facial detection and expression/gender classification based on Keras CNN models with OpenCV, trained with fer2013/imdb dataset
Number of GitHub stars: 1967
链接：
https://github.com/oarriaga/face_classification
No.22 Speech to Text WaveNet：使用 DeepMind 的 WaveNet 和 TensorFlow 构成的端到端句级英语语音识别
GitHub stars数: 1961个
Source: Namju Kim of Kakao Brain
链接：
https://github.com/buriburisuri/speech-to-text-wavenet
No.23 StarGAN： Unified generative adversarial networks for multi-domain image-to-image conversion
GitHub stars数: 1954个
Source: Yunjey Choi, Korea University
链接：
https://github.com/yunjey/StarGAN
No.24 MI-agents： Unity Machine Learning Intelligence Body
GitHub stars数: 1658个
Source: Arthur Juliani of Deep Learning Unity3D
链接：
https://github.com/Unity-Technologies/ml-agents
No.25 Deep Video Analytics：Distributed visual search and visual data analysis platform
GitHub stars数: 1494个
Source: Akshay Bhat, Cornell University
No.26 OpenNMT：Torch 上的开源神经机器翻译
Number of GitHub stars: 1,490
链接：
https://github.com/OpenNMT/OpenNMT
No.27 Pix2PixHD：使用条件 GAN 合成和处理 2048×1024 分辨率的图像
GitHub stars数：1283个
来源：英伟达 AI 科学家 Ming-Yu Liu
链接：
https://github.com/NVIDIA/pix2pixHD
No.28 Horovod：分布式 TensorFlow 训练框架
Number of GitHub stars: 1188
Source: Uber Engineering Team
链接：
https://github.com/uber/horovod
No.29 AI-Blocks： Powerful and intuitive WYSIWYG interface that allows anyone to create machine learning models
Number of GitHub stars: 899
链接：
https://github.com/MrNothing/AI-Blocks
No.30 Voice Conversion with Non-Parallel Data：基于 TensorFlow 的深度神经网络语音转换（语音风格转换）
Number of GitHub stars: 845
Source: Dabi Ahn, Kakao Brain AI Research Team
链接：
https://github.com/andabi/deep-voice-conversion
https://medium.mybridge.co/30-amazing-machine-learning-projects-for-the-past-year-v-2018-b853b8621ac7
[Machine Learning Concept of the Day]
Have a Great Definition
志愿者介绍
Reply "Volunteer" to join us
Recommended>>
1、Dare to be Software The Worlds First IoT EcoOperating System Enterprise
2、2018 what new trends will come out of Chinas artificial intelligence
3、Python stuff
4、The useful and interesting timestamp in blockchain you may not believe it its amazing
5、DeskBellChain creates the hotel ecosystem with blockchain and release is on the horizon