The most popular 30 open source machine learning program in the 2017 GitHub

Source: Internet
Author: User
Tags pytorch
What machine learning programs have been the most watched in 2017 years. Mybridge a list of top 30 for us, with GitHub links attached to all of the following items.


We compared nearly 8,800 Kaiyuan machine learning programs and selected the best of the 30. This is a very competitive list of all the outstanding machine learning libraries, datasets, and applications for January 2017-December open source. Mybridge AI Ratings by popularity, participation, and freshness. Let me first give you a visual impression: their GitHub average stars are 3,558.


Open source projects are very meaningful for data scientists, and we can build more powerful projects on the basis of our predecessors by reading the source code. Now, you can try these last year's best projects.




No.1


Fasttext: Quick text representation/classification library, from Facebook (GitHub 11,786 stars)


Link: https://github.com/facebookresearch/fastText


Content reference to: Facebook releases new fasttext: Expand to Mobile end, add tutorials


PS Muse: Multi-lingual unsupervised/supervised word embedding, based on Fasttext (GitHub 695 stars)


Link: Https://github.com/facebookresearch/MUSE


No.2


Deep-photo-styletransfer: Code and data for Deep photo Style Transfer, Cornell University Fujun Luan (GitHub 9747 stars)


Link: https://github.com/luanfujun/deep-photo-styletransfer


No.3


Face recognition: The simplest Python command line facial recognition API from Adam geitgey (GitHub 8672 stars)


Link: https://github.com/ageitgey/face_recognition


Content reference to: Open source face recognition library based on Python: off-line recognition rate up to 99.38%


No.4


Magenta: Machine Intelligent music and art builder (GitHub 8113 stars)


Link: Https://github.com/tensorflow/magenta


Content reference to: Google Magenta Project is how to teach the neural network to write music.


No.5


Sonnet: Neural network base based on TensorFlow (GitHub 5731 stars), from DeepMind member Malcolm Reynolds


Link: https://github.com/deepmind/sonnet


Content reference to: DeepMind Open source Sonnet: Can quickly build neural network in TensorFlow


No.6


Deeplearn.js: web-side hardware acceleration machine learning Library from Google Brain team Nikhil Thorat (GitHub 5462 stars)


Link: https://github.com/PAIR-code/deeplearnjs


Content reference to: Google Open source deeplearn.js: On the Web page to achieve hardware accelerated machine learning


No.7


Fast style transfer:tensorflow quick stylistic conversion from the Logan Engstrom (GitHub 4843 stars) at MIT


Link: https://github.com/lengstrom/fast-style-transfer


No.8


PYSC2: StarCraft 2 learning environment, from DeepMind Timo Ewalds and others (GitHub 3683 stars)


Link: https://github.com/deepmind/pysc2


No.9


Airsim: Open source autopilot simulator based on Unreal Engine, proposed by Microsoft Research Shital Shah and others (GitHub 3861 stars)


Link: Https://github.com/Microsoft/AirSim


No.10


Facets: Machine learning DataSet visualization tool, from Google Brain (GitHub 3371 stars)


Link: https://github.com/PAIR-code/facets


Content reference to: Google Open source machine learning visualization tool Facets: Look at the data from a new angle


No.11


Style2paints:ai Comic Line coloring tool from Suzhou University (GitHub 3310 Stars)


Link: https://github.com/lllyasviel/style2paints


Content reference to: style2paints: Professional AI comic line automatic coloring tool


No.12


Tensor2tensor: Tool library for generalized sequence-sequence models, from Ryan Sepassi of Google Brain (GitHub 3087 stars)


Link: https://github.com/tensorflow/tensor2tensor


Content reference to: A model library learn all: Google Open source modular depth Learning system tensor2tensor


No.13


Cyclegan and Pix2pix in Pytorch: Pytorch-based image-image conversion tool, from UC Berkeley, PhD Zhu Junyan (GitHub 2847 stars)


Link: Https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix


Reference content: You come to hand-painted graffiti, artificial intelligence generated "cat slice":edges2cats image Conversion


No.14


Faiss: A tool library for searching and clustering with dense vector-efficient similarity, from Facebook (GitHub 2629 stars)


Link: Https://github.com/facebookresearch/faiss


No.15


Fashion-mnist: A fashion product dataset similar to Mnist, from Han Xiao of Zalando Tech (GitHub 2780 stars)


Link: https://github.com/zalandoresearch/fashion-mnist


No.16


Parlai: Framework for training and evaluating AI models on a variety of publicly available conversation datasets, Alexander Miller (GitHub 2578 stars) from Facebook


Link: Https://github.com/facebookresearch/ParlAI


Content reference to: Facebook Open source AI framework Parlai: Easy Training Assessment Dialog model


No.17


Fairseq: Sequences from FAIR to sequence kits (GitHub 2571 stars)


Link: https://github.com/facebookresearch/fairseq


Content reference to: Facebook proposes new CNN machine translation: Accuracy beyond Google and is nine times times faster (open source)


No.18


Pyro: Use Python and pytorch for depth general probability programming, from Uber AI Labs (GitHub 2387 stars)


Link: Https://github.com/uber/pyro


Content reference to: Uber and Stanford University open source depth probability programming language pyro: Based on Pytorch


No.19


IgAN: An interactive image generator based on GAN (GitHub 2369 stars)


Link: Https://github.com/junyanz/iGAN


Content reference to: University of Berkeley and Adobe Open source depth learning image editing Tool IgAN


No.20


Deep-image-prior: Using neural networks for image recovery without learning process, from Skoltech's Ulyanov (GitHub 2188 stars)


Link: https://github.com/DmitryUlyanov/deep-image-prior


No.21


Face classification: Real-time facial detection and expression/sex classification based on Keras CNN model and OpenCV, training and Fer2013/imdb data sets (GitHub 1967 stars)


Link: https://github.com/oarriaga/face_classification


No.22


Speech to Text wavenet: Use DeepMind wavenet and TensorFlow to form an end-to-end sentence-level English speech recognition, Kakao Brain from Namju Kim (GitHub 1961 stars)


Link: https://github.com/buriburisuri/speech-to-text-wavenet


Content reference to: DeepMind wavenet, the machine synthetic voice level and the human gap reduced by 50%


No.23


Stargan: A unified generation confrontation network for multi-domain image-image conversion (GitHub 1954 stars)


Link: Https://github.com/yunjey/StarGAN


No.24


Mi-agents:unity machine learning agent, Arthur Juliani from Unity3d (GitHub 1658 stars)


Link: https://github.com/Unity-Technologies/ml-agents


No.25


Deep Video Analytics: Distributed visual search and visualization data analysis platform, from Cornell University's Akshay Bhat (GitHub 1494 stars)


Link: https://github.com/AKSHAYUBHAT/DeepVideoAnalytics


No.26


Open source neural machine translation on Opennmt:torch (GitHub 1490 stars)


Link: Https://github.com/OpenNMT/OpenNMT


Content reference to: Harvard University NLP Group Open Source Neural Machine Translation Toolkit OPENNMT: Production available level has been reached


No.27


PIX2PIXHD: Using conditional GAN to synthesize and process 2048x1024 resolution images from NVIDIA AI scientist Ming-yu Liu (GitHub 1283 stars)


Link: Https://github.com/NVIDIA/pix2pixHD


No.28


HOROVOD: Distributed TensorFlow Training Framework, from Uber Engineering team (GitHub 1188 stars)


Link: Https://github.com/uber/horovod


Content reference to: detailed Horovod:uber open source TensorFlow distributed depth Learning framework


No.29


Ai-blocks: A powerful and intuitive WYSIWYG interface that allows anyone to create a machine learning model (GitHub 899 stars)


Link: https://github.com/MrNothing/AI-Blocks


No.30


Voice conversion with Non-parallel Data: Deep Neural network voice conversion based on TensorFlow (voice-style conversion) from Kakao Brain team Dabi Ahn (GITHUB)


Link: https://github.com/andabi/deep-voice-conversion


Original link: https://medium.mybridge.co/30-amazing-machine-learning-projects-for-the-past-year-v-2018-b853b8621ac7


Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.