【导读】近日,Mybridge发布了一篇博文,总结了在过去一年中机器学习、深度学习领域全球流行的开源项目。作者从8800个GitHub的开源项目中筛选出30个2017年最炙手可热项目,这些项目都是在2017年1~12月发布的,其中不乏像FastText、deeplearn.js等已广为人知的精品,或许还有很多你并未关注但是同样优秀的项目。下面就让我们一睹它们风采吧。
我们总结了过去一年中8800个开源的机器学习项目,并从中选出Top 30个最受欢迎的项目
这个名单非常具有含金量,它包含了过去一年(发布于2017年1~12月期间)最好的开源机器学习库、数据集和应用程序。mybridge AI评价质量考虑普及,参与和近因。给你一个关于质量的想法,Mybridge AI通过考虑项目的知名度、参与度和是否最新来评估这些开源项目的质量,这些项目在Github中平均有3558个stars。
开源项目对搞科研的人来说非常重要,因为你不仅可以阅读源码了解作者的思想,还可以基于源码构建自己的项目。
在此之前,我们推荐学习以下内容:
A. 神经网络:
——推荐次数68,745 , 4.5/5 stars
链接:http://bit.ly/2CH1WcQ
B. TensorFlow:用python进行深度学习的指南
——推荐次数17,834, 4.6/5 stars
链接:http://bit.ly/2EatVy7
接下来给大家介绍Top 30的项目:
▌1. FastText: Library for fast text representation and classibcation.
FastText:快速文本表示和文本分类的库【Github上有11786颗星】
链接:
https://github.com/facebookresearch/fastText?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
贡献者:
Facebook Research https://medium.com/@FBResearch
[灵感来自:基于快速文本的多语言无监督或监督词嵌入。 Github上有695颗星]
链接:
https://github.com/facebookresearch/MUSE
▌2. Deep-photo-styletransfer: Code and data for paper “Deep Photo Style Transfer”
照片风格转换:源码和数据都来自论文“Deep Photo Style Transfer” 【GitHub 9747颗星】
贡献者:Fujun Luan, Ph.D. Cornell University
链接:
https://github.com/luanfujun/deep-photo-styletransfer?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌3. The world’s simplest facial recognition api for Python and the command line
The world’s simplest facial recognition api for Python and the command line
Python实现的世界上最简单的人脸识别API 【GitHub 8672颗星】
贡献者:Adam Geitgey
链接:
https://github.com/ageitgey/face_recognition?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌4. Magenta: Music and Art Generation with Machine Intelligence
利用机器智能生成音乐和美术作品
【GitHub 8113颗星】
链接:
https://github.com/tensorflow/magenta?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌5. Sonnet: TensorFlow-based neural network library
Sonnet: 基于TensorFlow的神经网络库
【GitHub 573颗星】
贡献者:Malcolm Reynolds at Deepmind
链接:
https://github.com/deepmind/sonnet?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌6. deeplearn.js: A hardware-accelerated machine intelligence library for the web
deeplearn.js: 一个用硬件加速的web深度学习库
【GitHub 5462颗星】
贡献者:Courtesy of Nikhil Thorat at Google Brain
链接:
https://github.com/PAIR-code/deeplearnjs?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌7. Fast Style Transfer in TensorFlow
基于TensorFlow的快速风格转换
【GitHub 4843颗星】
贡献者:Logan Engstrom at MIT
链接:
https://github.com/lengstrom/fast-style-transfer?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌8. Pysc2: StarCraft II Learning Environment
Pysc2: 星际争霸2学习环境
【GitHub 3684颗星】
贡献者:Timo Ewalds at DeepMind
链接:
https://github.com/deepmind/pysc2?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌9. AirSim: Open source simulator based on Unreal Engine for autonomous vehicles from Microsoft AI & Research
AirSim: Microsoft AI & Research的基于虚拟引擎的开源模拟器——用于自动驾驶
【GitHub 3861颗星】
贡献者:Shital Shah at Microsoft
链接:
https://github.com/Microsoft/AirSim?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌10. acets: Visualizations for machine learning datasets
acets: 机器学习数据集可视化
【GitHub 3371颗星】
贡献者:Google Brain
链接:
https://github.com/PAIR-code/facets?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌11. Style2Paints: AI colorization of images
线稿上色:利用AI着色
【GitHub 3310颗星】
链接:
https://github.com/lllyasviel/style2paints?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌12. Tensor2Tensor: A library for generalized sequence to sequence models—Google Research
Tensor2Tensor:序列-序列模型泛化库--Google Research
【GitHub 3087颗星】
贡献者:Ryan Sepassi at Google Brain
链接:
https://github.com/tensorflow/tensor2tensor?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌13. Image-to-image translation in PyTorch
Pytorch实现的图片-图片转化
【GitHub 2847颗星】
贡献者:Jun-Yan Zhu, Ph.D at Berkeley
链接:
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌14. Faiss: A library for ejcient similarity search and clustering of dense vectors.
Faiss: 用于稠密向量高效聚类和相似性搜索库
【GitHub 2629颗星】
贡献者:Facebook Research
链接:
https://github.com/facebookresearch/faiss?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌15. Fashion-mnist: A MNIST-like fashion product database
Fashion-minist: 一个类似于MNIST的时尚产品数据库
【GitHub 2780颗星】
贡献者: Han Xiao, Research Scientist Zalando Tech
链接:
https://github.com/zalandoresearch/fashion-mnist?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌16. ParlAI: A framework for training and evaluating AI models on a variety of openly available dialog datasets
ParlAI: 一个可以在多种开源对话数据集上训练和评价AI模型的框架
【GitHub 2578颗星】
贡献者:Alexander Miller at Facebook Research
链接:
https://github.com/facebookresearch/ParlAI?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌17. Fairseq: Facebook AI Research Sequence-to-Sequence Toolkit
Fairseq: Facebook 的序列-序列工具箱
【GitHub 2571颗星】
链接:
https://github.com/facebookresearch/fairseq?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌18. Pyro: Deep universal probabilistic programming with Python and PyTorch
Pyro: 基于Python和PyTorch的通用的深度概率编程
【GitHub 2387颗星】
贡献者:Uber Engineering
链接:
https://github.com/uber/pyro?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌19. iGAN: Interactive Image Generation powered by GAN
iGAN: 基于GAN的交互式图像生成
【GitHub 2369颗星】
链接:
https://github.com/junyanz/iGAN?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌20. Deep-image-prior: Image restoration with neural networks but without learning
深度图像先验:不进行学习的神经网络图像恢复
【GitHub 2188颗星】
贡献者:Dmitry Ulyanov, Ph.D at Skoltech
链接:
https://github.com/DmitryUlyanov/deep-image-prior?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌21. Face_classibcation: Real-time face detection and emotion/gender classibcation using fer2013/imdb datasets with a keras CNN model and openCV.
人脸分类:实时人脸检测和情感识别/使用fer2013进行性别识别/在imdb数据集上使用keras CNN模型和openCV
【GitHub 1967颗星】
链接:
https://github.com/oarriaga/face_classification?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌22. Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition using DeepMind’s WaveNet and tensorflow
Speech-to-Text-WaveNet: 使用DeepMind的WaveNet和TensorFlow进行端到端的英语语音识别
【GitHub 1961颗星】
贡献者:Namju Kim at Kakao Brain
链接:
https://github.com/buriburisuri/speech-to-text-wavenet?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌23. StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
StarGAN: 用于多域图像-图像转化的统一生成对抗网络
【GitHub 1954颗星】
贡献者:Yunjey Choi at Korea University
链接:
https://github.com/yunjey/StarGAN?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌24. Ml-agents: Unity Machine Learning Agents
MI-agents: 机器学习统一代理
【GitHub 1658颗星】
贡献者:Arthur Juliani, Deep Learning at Unity3D
链接:
https://github.com/Unity-Technologies/ml-agents?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌25. DeepVideoAnalytics: A distributed visual search and visual data analytics platform
DeepVideoAnalytics:一个分布式可视化搜索和分析平台
【GitHub 1494颗星】
贡献者:Akshay Bhat, Ph.D at Cornell University
链接:
https://github.com/AKSHAYUBHAT/DeepVideoAnalytics/?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌26. OpenNMT: Open-Source Neural Machine Translation in Torch
OpenNMT: Torch的神经机器翻译开源库
【GitHub 1490颗星】
链接:
https://github.com/OpenNMT/OpenNMT?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌27. Pix2pixHD: Synthesizing and manipulating 2048x1024 images with conditional GANs
Pix2pixHD: 用条件GAN合成和处理2048×1024的图像
【GitHub 1283颗星】
贡献者:Ming-Yu Liu at AI Research Scientist at Nvidia
链接:
https://github.com/NVIDIA/pix2pixHD?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌28. Horovod: Distributed training framework for TensorFlow
Horovod: TensorFlow分布式训练框架
【GitHub 1188颗星】
贡献者:Uber Engineering
链接:
https://github.com/uber/horovod?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌29. AI-Blocks: A powerful and intuitive WYSIWYG interface that allows anyone to create Machine Learning models
AI-Blocks: 一个强大而直观的、所见即所得的界面,允许任何人创建机器学习模型
【GitHub 899颗星】
链接:
https://github.com/MrNothing/AI-Blocks?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
▌30. Deep neural networks for voice conversion (voice style transfer) in Tensorflow
Tensorflow实现的深度神经网络进行语音转换(语音风格转换)
【GitHub 845颗星】
贡献者:Dabi Ahn, AI Research at Kakao Brain
链接:
https://github.com/andabi/deep-voice-conversion?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
原文链接:
https://medium.mybridge.co/30-amazing-machine-learning-projects-for-the-past-year-v-2018-b853b8621ac7
-END-
专 · 知
人工智能领域主题知识资料查看获取:【专知荟萃】人工智能领域26个主题知识资料全集(入门/进阶/论文/综述/视频/专家等)
同时欢迎各位用户进行专知投稿,详情请点击:
【诚邀】专知诚挚邀请各位专业者加入AI创作者计划!了解使用专知!
请PC登录www.zhuanzhi.ai或者点击阅读原文,注册登录专知,获取更多AI知识资料!
请扫一扫如下二维码关注我们的公众号,获取人工智能的专业知识!
请加专知小助手微信(Rancho_Fang),加入专知主题人工智能群交流!
点击“阅读原文”,使用专知!