在過去的一年裡,Mybridge AI 比較了近 8,800個開源機器學習專案,選擇了前30名(概率只有0.3%)。
這是一個競爭激烈的名單,精挑細選了2017年1月到12月之間釋出的最佳開源機器學習庫、資料集和應用程式。Mybridge AI 通過考量受歡迎程度、參與度和新近度來等指標來評估這些參選專案的質量。這些專案在Github得星的數量平均為3,558個,其質量相當不錯。
開源專案對資料科學家來說可能大有裨益。 通過閱讀原始碼並在現有專案之上構建一些東西來可以加快學習步伐。是該拿出時間來玩玩過去一年中可能錯過的機器學習專案啦!
推薦閱讀文章
在看排名清單之前,建議首先看看下面2篇文章:
A)神經網路
深度學習A-Z™:動手的人工神經網路(Deep Learning A-Z™: Hands-On Artificial Neural Networks)http://bit.ly/2CH1WcQ
[68,745條推薦,4.5 / 5星]
B)TensorFlow
用Python進行深度學習的TensorFlow完整指南(Complete Guide to TensorFlow for Deep Learning with Python)http://bit.ly/2EatVy7
[17,834條推薦,4.6 / 5星]
開源專案排行榜
第 1 名
FastText:用於快速文字表示和分類的庫(FastText: Library for fast text representation and classification)。https://goo.gl/VWGfCs
[Github上的11786顆星] 由Facebook Research提供
…[Muse: 基於快速文字的多語言無監督或監督詞嵌入(Muse: Multilingual Unsupervised or Supervised word Embeddings, based on Fast Text)。
Github上的695顆星] https://goo.gl/stbhjZ
第 2 名
深色照片風格轉換:論文“深度照片風格轉移”程式碼和資料(Deep-photo-styletransfer: Code and data for paper “Deep Photo Style Transfer”) https://github.com/luanfujun/deep-photo-styletransfer?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上的9747顆星星] 由康奈爾大學 Fujun Luan 博士提供
第 3 名
Python和世界上最簡單的面部識別api和命令列(The world’s simplest facial recognition api for Python and the command line)https://github.com/ageitgey/face_recognition?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上8672個星] 由Adam Geitgey提供
第 4 名
洋紅(Magenta: ):機器智慧生成音樂和藝術(Magenta: Music and Art Generation with Machine Intelligence)。https://github.com/tensorflow/magenta?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[GitHub上 8113顆星]
第 5 名
Sonnet:基於TensorFlow的神經網路庫(Sonnet: TensorFlow-based neural network library)https://github.com/deepmind/sonnet?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上5731顆星]。 由Deepmind公司的Malcolm Reynolds(https://medium.com/@malcolm.reynolds)提供
第 6 名
deeplearn.js:為Web提供硬體加速的機器智慧庫(https://github.com/PAIR-code/deeplearnjs?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上5462顆星]。 由Google Brain的Nikhil Thorat提供
第 7 名
TensorFlow的快速風格遷移(Fast Style Transfer in TensorFlow)https://github.com/lengstrom/fast-style-transfer?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上4843顆星] 由MIT的Logan Engstrom提供
第 8 名
Pysc2:星際爭霸II學習環境(Pysc2: StarCraft II Learning Environment)https://github.com/deepmind/pysc2?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上3683顆星星] 由DeepMind的Timo Ewalds提供
第 9 名
AirSim:基於Unreal Engine的開源模擬器,用於微軟AI&Research自主車輛(AirSim: Open source simulator based on Unreal Engine for autonomous vehicles from Microsoft AI & Research)https://github.com/Microsoft/AirSim?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上3861顆星]。 由Microsoft的Shital Shah提供
第 10 名
Facets: 機器學習資料集的視覺化(Facets: Visualizations for machine learning datasets)https://github.com/PAIR-code/facets?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上3371顆星] 由Google Brain提供
第 11 名
Style2Paints:影像的AI彩色化(Style2Paints: AI colorization of images)https://github.com/lllyasviel/style2paints?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上3310顆星]
第 12 名
Tensor2Tensor:Google Research的廣義序列到序列模型庫 (Tensor2Tensor: A library for generalized sequence to sequence models — Google Research )https://github.com/tensorflow/tensor2tensor?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上3087顆星] 由Google Brain的Ryan Sepassi提供
第 13 名
PyTorch中的影像到影像轉換(例如horse2zebra,edges2cats等)[Image-to-image translation in PyTorch (e.g. horse2zebra, edges2cats, and more)] https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上2847顆星] 由伯克利的Jun-Yan Zhu博士提供
第 14 名
Faiss:用於密集向量的高效相似性搜尋和聚類的庫(Faiss: A library for efficient similarity search and clustering of dense vectors)https://github.com/facebookresearch/faiss?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上2629顆星]。 由Facebook Research提供
第 15 名
Fashion-mnist:類似MNIST的時尚產品資料庫(Fashion-mnist: A MNIST-like fashion product database)https://github.com/zalandoresearch/fashion-mnist?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上2780顆星星] 由Zalando Tech的研究科學家Han Xiao提供
第 16 名
ParlAI:在各種公開可用的對話資料集上訓練和評估AI模型的框架(https://github.com/facebookresearch/ParlAI?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more)
[Github上2578顆星]。 有Facebook研究院的Alexander Miller提供
第 17 名
Fairseq:Facebook AI研究序列 – 序列工具包(Fairseq: Facebook AI Research Sequence-to-Sequence Toolkit)https://github.com/facebookresearch/fairseq?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上2571顆星]
第 18 名
Pyro:Python和PyTorch的深度通用概率程式設計(Pyro: Deep universal probabilistic programming with Python and PyTorch)https://github.com/uber/pyro?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上的2387顆星] 由Uber Engineering提供
第 19 名
iGAN:由GAN支援的互動式影像生成(iGAN: Interactive Image Generation powered by GAN)https://github.com/junyanz/iGAN?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上2369顆星]
::__IHACKLOG_REMOTE_IMAGE_AUTODOWN_BLOCK__::21
第 20 名
Deep-image-prior:使用無需學習的神經網路進行影像恢復(Deep-image-prior: Image restoration with neural networks but without learning)https://github.com/DmitryUlyanov/deep-image-prior?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上2188顆星] 由Skoltech博士Dmitry Ulyanov提供
第 21 名
Face_classification:使用具有keras CNN模型和openCV的fer2013 / imdb資料集的實時人臉檢測和情感/性別分類(Face_classification: Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV)https://github.com/oarriaga/face_classification?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1967星]
第 22 名
Speech-to-Text-WaveNet:使用DeepMind的WaveNet和tensorflow進行端到端的句子級英語語音識別(Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition using DeepMind’s WaveNet and tensorflow )https://github.com/buriburisuri/speech-to-text-wavenet?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1961星] 由Kakao Brain的Namju Kim提供
第 23 名
StarGAN:用於多域影像到影像轉換的統一生成對抗網路(StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation)https://github.com/yunjey/StarGAN?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1954顆星] 由韓國大學的Yunjey Choi提供
第 24 名
Ml-agents:Unity機器學習代理(Ml-agents: Unity Machine Learning Agents)
[Github上的1658顆星] Deep Learning at Unity3D 的Unity Juliani提供
第 25 名
DeepVideoAnalytics:分散式視覺化搜尋和視覺化資料分析平臺(DeepVideoAnalytics: A distributed visual search and visual data analytics platform)https://github.com/AKSHAYUBHAT/DeepVideoAnalytics/?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1494顆星] 由康奈爾大學的Akshay Bhat博士提供
第 26 名
OpenNMT:火炬中的開源神經機器翻譯(OpenNMT: Open-Source Neural Machine Translation in Torch)https://github.com/OpenNMT/OpenNMT?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1490顆星]
第 27 名
Pix2pixHD:使用條件GAN合成和處理2048×1024的影像(Pix2pixHD: Synthesizing and manipulating 2048×1024 images with conditional GANs )https://github.com/NVIDIA/pix2pixHD?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1283顆星] 由Nvidia的AI Research 科學家 Ming-Yu Liu提供
第 28 名
Horovod:TensorFlow的分散式訓練框架(Horovod: Distributed training framework for TensorFlow) https://github.com/uber/horovod?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上1188顆星] 由Uber Engineering提供
第 29 名
AI-Blocks: 強大的和直觀的所見即所得的介面,允許任何人建立的機器學習模型(AI-Blocks: A powerful and intuitive WYSIWYG interface that allows anyone to create Machine Learning models)https://github.com/MrNothing/AI-Blocks?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[GitHub上 899顆星]
第 30 名
採用Tensorflow的深度神經網路進行語音轉換(語音風格遷移)[Deep neural networks for voice conversion (voice style transfer) in Tensorflow] https://github.com/andabi/deep-voice-conversion?utm_source=mybridge&utm_medium=blog&utm_campaign=read_more
[Github上845顆星] 有AI Kakao Brain的AI 研究院的Dabi Ahn提供
參考文章:
30 Amazing Machine Learning Projects for the Past Year
https://medium.mybridge.co/30-amazing-machine-learning-projects-for-the-past-year-v-2018-b853b8621ac7