【Deep Learning】Github上关注最多的53个深度学习项目

太过爱你忘了你带给我的痛 2022-09-25 04:18 5阅读 0赞

# Top Deep Learning Projects #

A list of popular github projects related to deep learning (ranked by stars).

Last Update: 2016.08.09

<table> 
 <thead> 
  <tr> 
   <th align="left">项 目 名 称</th> 
   <th align="center">Stars</th> 
   <th align="left">项目介绍</th> 
  </tr> 
 </thead> 
 <tbody> 
  <tr> 
   <td align="left">TensorFlow</td> 
   <td align="center">29622</td> 
   <td align="left">使用数据流图计算可扩展机器学习问题</td> 
  </tr> 
  <tr> 
   <td align="left">Caffe</td> 
   <td align="center">11799</td> 
   <td align="left">Caffe是一个高效的开源深度学习框架</td> 
  </tr> 
  <tr> 
   <td align="left">Neural Style</td> 
   <td align="center">10148</td> 
   <td align="left">Torch实现的神经网络算法</td> 
  </tr> 
  <tr> 
   <td align="left">Deep Dream</td> 
   <td align="center">9042</td> 
   <td align="left">Deep Dream，一款图像识别工具</td> 
  </tr> 
  <tr> 
   <td align="left">Keras</td> 
   <td align="center">7502</td> 
   <td align="left">一款Python实现的深度学习库，包括卷积神经网络、递归神经网络等。运行在Theano和TensorFlow之上。</td> 
  </tr> 
  <tr> 
   <td align="left">Roc AlphaGo</td> 
   <td align="center">7170</td> 
   <td align="left">学生主导的一个独立项目，从新实现了 DeepMind在2016 Nature发表的内容， 《用深度神经网络和树搜索学习围棋》 (Nature 529, 484-489, 28 Jan 2016).</td> 
  </tr> 
  <tr> 
   <td align="left">TensorFlow Models</td> 
   <td align="center">6671</td> 
   <td align="left">基于TensorFlow开发的模型</td> 
  </tr> 
  <tr> 
   <td align="left">Neural Doodle</td> 
   <td align="center">6275</td> 
   <td align="left">运用深度神经网络将涂鸦变为优雅的艺术品，从照片生成无缝纹理，转变图片风格，进行基于实例的提升，等等…还有更多！（语义风格传递的实现）</td> 
  </tr> 
  <tr> 
   <td align="left">CNTK</td> 
   <td align="center">5957</td> 
   <td align="left">计算网络工具（Computational Network Toolkit，CNTK）</td> 
  </tr> 
  <tr> 
   <td align="left">TensorFlow Examples</td> 
   <td align="center">5872</td> 
   <td align="left">初学者的TensorFlow教程和代码示例。</td> 
  </tr> 
  <tr> 
   <td align="left">ConvNet JS</td> 
   <td align="center">5231</td> 
   <td align="left">基于Javascript的深度学习库。在浏览器中训练卷积神经网络模型（或者普通模型）。</td> 
  </tr> 
  <tr> 
   <td align="left">Torch</td> 
   <td align="center">5133</td> 
   <td align="left">Torch7，深度学习库。</td> 
  </tr> 
  <tr> 
   <td align="left">OpenFace</td> 
   <td align="center">4855</td> 
   <td align="left">基于深度学习网络的面部识别。</td> 
  </tr> 
  <tr> 
   <td align="left">MXNet</td> 
   <td align="center">4685</td> 
   <td align="left">轻巧、便携、灵活的分布式/移动深度学习框架，支持Python, R, Julia, Scala, Go, Javascript等等语言。</td> 
  </tr> 
  <tr> 
   <td align="left">Nupic</td> 
   <td align="center">4364</td> 
   <td align="left">智能计算的Numenta平台：一个脑启发式的计算智能和机器智能平台，基于皮层学习算法的生物精确神经网络模型。</td> 
  </tr> 
  <tr> 
   <td align="left">Theano</td> 
   <td align="center">4286</td> 
   <td align="left">Theano 是一个 Python 库,用来定义、优化和模拟数学表达式计算,用于高效的解决多维数组的计算问题。</td> 
  </tr> 
  <tr> 
   <td align="left">Leaf</td> 
   <td align="center">4281</td> 
   <td align="left">黑客的开源机器智能框架。</td> 
  </tr> 
  <tr> 
   <td align="left">Char RNN</td> 
   <td align="center">3820</td> 
   <td align="left">多层递归神经网络的字符级别语言模型，基于Torch开发。</td> 
  </tr> 
  <tr> 
   <td align="left">Neural Talk</td> 
   <td align="center">3694</td> 
   <td align="left">NeuralTalk是一个Python+numpy项目，用多模式递归神经网络描述图像。</td> 
  </tr> 
  <tr> 
   <td align="left">deeplearning4j</td> 
   <td align="center">3673</td> 
   <td align="left">基于Hadoop和Spark的Java, Scala &amp; Clojure深度学习工具。</td> 
  </tr> 
  <tr> 
   <td align="left">TFLearn</td> 
   <td align="center">3368</td> 
   <td align="left">深度学习库，包括高层次的TensorFlow接口。</td> 
  </tr> 
  <tr> 
   <td align="left">TensorFlow Playground</td> 
   <td align="center">3352</td> 
   <td align="left">神经网络模型示例。</td> 
  </tr> 
  <tr> 
   <td align="left">OpenAI Gym</td> 
   <td align="center">3020</td> 
   <td align="left">一种用于开发和比较强化学习算法的工具包。</td> 
  </tr> 
  <tr> 
   <td align="left">Magenta</td> 
   <td align="center">2914</td> 
   <td align="left">Magenta: 音乐和艺术的生成与机器智能</td> 
  </tr> 
  <tr> 
   <td align="left">Colornet</td> 
   <td align="center">2798</td> 
   <td align="left">用神经网络模型给灰度图上色。</td> 
  </tr> 
  <tr> 
   <td align="left">Synaptic</td> 
   <td align="center">2666</td> 
   <td align="left">基于node.js和浏览器的免架构神经网络库。</td> 
  </tr> 
  <tr> 
   <td align="left">Neural Talk 2</td> 
   <td align="center">2550</td> 
   <td align="left">Torch开发的图像简介生成代码，运行在GPU上。</td> 
  </tr> 
  <tr> 
   <td align="left">Image Analogies</td> 
   <td align="center">2540</td> 
   <td align="left">使用神经匹配和融合生成相似图形。</td> 
  </tr> 
  <tr> 
   <td align="left">TensorFlow Tutorials</td> 
   <td align="center">2413</td> 
   <td align="left">Tensorflow，从基础原理到应用。</td> 
  </tr> 
  <tr> 
   <td align="left">Lasagne</td> 
   <td align="center">2355</td> 
   <td align="left">基于Theano训练和构建神经网络的轻型函数库。</td> 
  </tr> 
  <tr> 
   <td align="left">PyLearn2</td> 
   <td align="center">2153</td> 
   <td align="left">基于Theano的机器学习库。</td> 
  </tr> 
  <tr> 
   <td align="left">LISA-lab Deep Learning Tutorials</td> 
   <td align="center">2134</td> 
   <td align="left">深度学习教程笔记和代码。详情参见wiki页面。</td> 
  </tr> 
  <tr> 
   <td align="left">Neon</td> 
   <td align="center">2121</td> 
   <td align="left">Nervana™开发的一款快速、可扩展、易上手的Python深度学习框架.</td> 
  </tr> 
  <tr> 
   <td align="left">Matlab Deep Learning Toolbox</td> 
   <td align="center">2032</td> 
   <td align="left">Matlab/Octave的深度学习工具箱。包括深度信念网络、自动编码机、卷积神经网络、卷积自动编码机和vanilla神经网络等。每种方法都有入门示例。</td> 
  </tr> 
  <tr> 
   <td align="left">Deep Learning Flappy Bird</td> 
   <td align="center">1721</td> 
   <td align="left">使用深度强化学习破解Flappy Bird游戏(深度 Q-学习).</td> 
  </tr> 
  <tr> 
   <td align="left">Chainer</td> 
   <td align="center">1573</td> 
   <td align="left">一款灵活的深度学习神经网络框架。</td> 
  </tr> 
  <tr> 
   <td align="left">Neural Story Teller</td> 
   <td align="center">1514</td> 
   <td align="left">看图讲故事的递归神经网络模型。</td> 
  </tr> 
  <tr> 
   <td align="left">DIGITS</td> 
   <td align="center">1353</td> 
   <td align="left">深度学习GPU训练系统。</td> 
  </tr> 
  <tr> 
   <td align="left">Deep Jazz</td> 
   <td align="center">1229</td> 
   <td align="left">基于Keras和Theano生成jazz的深度学习模型！</td> 
  </tr> 
  <tr> 
   <td align="left">Brainstorm</td> 
   <td align="center">1143</td> 
   <td align="left">快速、灵活、有趣的神经网络。</td> 
  </tr> 
  <tr> 
   <td align="left">Darknet</td> 
   <td align="center">937</td> 
   <td align="left">C语言版本的开源神经网络。</td> 
  </tr> 
  <tr> 
   <td align="left">Theano Tutorials</td> 
   <td align="center">904</td> 
   <td align="left">基于Theano的机器学习入门教程，从线性回归到卷积神经网络。</td> 
  </tr> 
  <tr> 
   <td align="left">RNN Music Composition</td> 
   <td align="center">904</td> 
   <td align="left">一款生成古典音乐的递归神经网络工具。</td> 
  </tr> 
  <tr> 
   <td align="left">Blocks</td> 
   <td align="center">866</td> 
   <td align="left">用于构建和训练神经网络模型的Theano框架。</td> 
  </tr> 
  <tr> 
   <td align="left">TDB</td> 
   <td align="center">860</td> 
   <td align="left">TensorFlow的交互式、节点调试和可视化的工具。</td> 
  </tr> 
  <tr> 
   <td align="left">Scikit Neural Net</td> 
   <td align="center">849</td> 
   <td align="left">深度神经网络入门工具，类似scikit-learn的分类器和回归模型。</td> 
  </tr> 
  <tr> 
   <td align="left">Veles</td> 
   <td align="center">760</td> 
   <td align="left">分布式机器学习平台(Python, CUDA, OpenCL)</td> 
  </tr> 
  <tr> 
   <td align="left">Deep Detect</td> 
   <td align="center">759</td> 
   <td align="left">基于C++11的深度学习接口和服务器，与Python绑定并支持Caffe。</td> 
  </tr> 
  <tr> 
   <td align="left">TensorFlow DeepQ</td> 
   <td align="center">759</td> 
   <td align="left">基于Google Tensorflow的深度Q学习演示。</td> 
  </tr> 
  <tr> 
   <td align="left">Caffe on Spark</td> 
   <td align="center">724</td> 
   <td align="left">基于Spark的Caffe。</td> 
  </tr> 
  <tr> 
   <td align="left">Nolearn</td> 
   <td align="center">702</td> 
   <td align="left">神经网络库的抽象，著名的Lasagne。</td> 
  </tr> 
  <tr> 
   <td align="left">DCGAN TensorFlow</td> 
   <td align="center">568</td> 
   <td align="left">基于tensorflow实现的深度卷积生成对抗网络。</td> 
  </tr> 
  <tr> 
   <td align="left">DeepCL</td> 
   <td align="center">413</td> 
   <td align="left">用于训练深度卷积神经网络模型的OpenCL库。</td> 
  </tr> 
 </tbody> 
</table>

#### **> 英文原版** ####

> <table> 
>  <thead> 
>   <tr> 
>    <th align="left">Project Name</th> 
>    <th align="center">St ars</th> 
>    <th align="left">Description</th> 
>   </tr> 
>  </thead> 
>  <tbody> 
>   <tr> 
>    <td align="left"><a href="https://github.com/tensorflow/tensorflow" rel="nofollow">TensorFlow</a></td> 
>    <td align="center">29622</td> 
>    <td align="left">Computation using data flow graphs for scalable machine learning.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/BVLC/caffe" rel="nofollow">Caffe</a></td> 
>    <td align="center">11799</td> 
>    <td align="left">Caffe: a fast open framework for deep learning.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/jcjohnson/neural-style" rel="nofollow">Neural Style</a></td> 
>    <td align="center">10148</td> 
>    <td align="left">Torch implementation of neural style algorithm.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/google/deepdream" rel="nofollow">Deep Dream</a></td> 
>    <td align="center">9042</td> 
>    <td align="left">Deep Dream.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/fchollet/keras" rel="nofollow">Keras</a></td> 
>    <td align="center">7502</td> 
>    <td align="left">Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/Rochester-NRT/RocAlphaGo" rel="nofollow">Roc AlphaGo</a></td> 
>    <td align="center">7170</td> 
>    <td align="left">An independent, student-led replication of DeepMind’s 2016 Nature publication, “Mastering the game of Go with deep neural networks and tree search” (Nature 529, 484-489, 28 Jan 2016).</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/tensorflow/models" rel="nofollow">TensorFlow Models</a></td> 
>    <td align="center">6671</td> 
>    <td align="left">Models built with TensorFlow</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/alexjc/neural-doodle" rel="nofollow">Neural Doodle</a></td> 
>    <td align="center">6275</td> 
>    <td align="left">Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait… there’s more! (An implementation of Semantic Style Transfer.)</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/Microsoft/CNTK" rel="nofollow">CNTK</a></td> 
>    <td align="center">5957</td> 
>    <td align="left">Computational Network Toolkit (CNTK).</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/aymericdamien/TensorFlow-Examples" rel="nofollow">TensorFlow Examples</a></td> 
>    <td align="center">5872</td> 
>    <td align="left">TensorFlow tutorials and code examples for beginners.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/karpathy/convnetjs" rel="nofollow">ConvNet JS</a></td> 
>    <td align="center">5231</td> 
>    <td align="left">Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/torch/torch7" rel="nofollow">Torch</a></td> 
>    <td align="center">5133</td> 
>    <td align="left">Torch7, Deep Learning Library.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/cmusatyalab/openface" rel="nofollow">OpenFace</a></td> 
>    <td align="center">4855</td> 
>    <td align="left">Face recognition with deep neural networks.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/dmlc/mxnet" rel="nofollow">MXNet</a></td> 
>    <td align="center">4685</td> 
>    <td align="left">Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/numenta/nupic" rel="nofollow">Nupic</a></td> 
>    <td align="center">4364</td> 
>    <td align="left">Numenta Platform for Intelligent Computing: a brain-inspired machine intelligence platform, and biologically accurate neural network based on cortical learning algorithms.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/Theano/Theano" rel="nofollow">Theano</a></td> 
>    <td align="center">4286</td> 
>    <td align="left">Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/autumnai/leaf" rel="nofollow">Leaf</a></td> 
>    <td align="center">4281</td> 
>    <td align="left">Open Machine Intelligence Framework for Hackers.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/karpathy/char-rnn" rel="nofollow">Char RNN</a></td> 
>    <td align="center">3820</td> 
>    <td align="left">Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/karpathy/neuraltalk" rel="nofollow">Neural Talk</a></td> 
>    <td align="center">3694</td> 
>    <td align="left">NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/deeplearning4j/deeplearning4j" rel="nofollow">deeplearning4j</a></td> 
>    <td align="center">3673</td> 
>    <td align="left">Deep Learning for Java, Scala &amp; Clojure on Hadoop, Spark.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/tflearn/tflearn" rel="nofollow">TFLearn</a></td> 
>    <td align="center">3368</td> 
>    <td align="left">Deep learning library featuring a higher-level API for TensorFlow.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/tensorflow/playground" rel="nofollow">TensorFlow Playground</a></td> 
>    <td align="center">3352</td> 
>    <td align="left">Play with neural networks!</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/openai/gym" rel="nofollow">OpenAI Gym</a></td> 
>    <td align="center">3020</td> 
>    <td align="left">A toolkit for developing and comparing reinforcement learning algorithms.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/tensorflow/magenta" rel="nofollow">Magenta</a></td> 
>    <td align="center">2914</td> 
>    <td align="left">Magenta: Music and Art Generation with Machine Intelligence</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/pavelgonchar/colornet" rel="nofollow">Colornet</a></td> 
>    <td align="center">2798</td> 
>    <td align="left">Neural Network to colorize grayscale images.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/cazala/synaptic" rel="nofollow">Synaptic</a></td> 
>    <td align="center">2666</td> 
>    <td align="left">architecture-free neural network library for node.js and the browser</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/karpathy/neuraltalk2" rel="nofollow">Neural Talk 2</a></td> 
>    <td align="center">2550</td> 
>    <td align="left">Efficient Image Captioning code in Torch, runs on GPU.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/awentzonline/image-analogies" rel="nofollow">Image Analogies</a></td> 
>    <td align="center">2540</td> 
>    <td align="left">Generate image analogies using neural matching and blending.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/pkmital/tensorflow_tutorials" rel="nofollow">TensorFlow Tutorials</a></td> 
>    <td align="center">2413</td> 
>    <td align="left">From the basics to slightly more interesting applications of Tensorflow.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/Lasagne/Lasagne" rel="nofollow">Lasagne</a></td> 
>    <td align="center">2355</td> 
>    <td align="left">Lightweight library to build and train neural networks in Theano.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/lisa-lab/pylearn2" rel="nofollow">PyLearn2</a></td> 
>    <td align="center">2153</td> 
>    <td align="left">A Machine Learning library based on Theano.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/lisa-lab/DeepLearningTutorials" rel="nofollow">LISA-lab Deep Learning Tutorials</a></td> 
>    <td align="center">2134</td> 
>    <td align="left">Deep Learning Tutorial notes and code. See the wiki for more info.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/NervanaSystems/neon" rel="nofollow">Neon</a></td> 
>    <td align="center">2121</td> 
>    <td align="left">Fast, scalable, easy-to-use Python based Deep Learning Framework by Nervana™.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/rasmusbergpalm/DeepLearnToolbox" rel="nofollow">Matlab Deep Learning Toolbox</a></td> 
>    <td align="center">2032</td> 
>    <td align="left">Matlab/Octave toolbox for deep learning. Includes Deep Belief Nets, Stacked Autoencoders, Convolutional Neural Nets, Convolutional Autoencoders and vanilla Neural Nets. Each method has examples to get you started.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/yenchenlin1994/DeepLearningFlappyBird" rel="nofollow">Deep Learning Flappy Bird</a></td> 
>    <td align="center">1721</td> 
>    <td align="left">Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/pfnet/chainer" rel="nofollow">Chainer</a></td> 
>    <td align="center">1573</td> 
>    <td align="left">A flexible framework of neural networks for deep learning.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/ryankiros/neural-storyteller" rel="nofollow">Neural Story Teller</a></td> 
>    <td align="center">1514</td> 
>    <td align="left">A recurrent neural network for generating little stories about images.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/NVIDIA/DIGITS" rel="nofollow">DIGITS</a></td> 
>    <td align="center">1353</td> 
>    <td align="left">Deep Learning GPU Training System.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/jisungk/deepjazz" rel="nofollow">Deep Jazz</a></td> 
>    <td align="center">1229</td> 
>    <td align="left">Deep learning driven jazz generation using Keras &amp; Theano!</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/IDSIA/brainstorm" rel="nofollow">Brainstorm</a></td> 
>    <td align="center">1143</td> 
>    <td align="left">Fast, flexible and fun neural networks.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/pjreddie/darknet" rel="nofollow">Darknet</a></td> 
>    <td align="center">937</td> 
>    <td align="left">Open Source Neural Networks in C</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/Newmu/Theano-Tutorials" rel="nofollow">Theano Tutorials</a></td> 
>    <td align="center">904</td> 
>    <td align="left">Bare bones introduction to machine learning from linear regression to convolutional neural networks using Theano.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/hexahedria/biaxial-rnn-music-composition" rel="nofollow">RNN Music Composition</a></td> 
>    <td align="center">904</td> 
>    <td align="left">A recurrent neural network designed to generate classical music.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/mila-udem/blocks" rel="nofollow">Blocks</a></td> 
>    <td align="center">866</td> 
>    <td align="left">A Theano framework for building and training neural networks.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/ericjang/tdb" rel="nofollow">TDB</a></td> 
>    <td align="center">860</td> 
>    <td align="left">Interactive, node-by-node debugging and visualization for TensorFlow.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/aigamedev/scikit-neuralnetwork" rel="nofollow">Scikit Neural Net</a></td> 
>    <td align="center">849</td> 
>    <td align="left">Deep neural networks without the learning cliff! Classifiers and regressors compatible with scikit-learn.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/samsung/veles" rel="nofollow">Veles</a></td> 
>    <td align="center">760</td> 
>    <td align="left">Distributed machine learning platform (Python, CUDA, OpenCL)</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/beniz/deepdetect" rel="nofollow">Deep Detect</a></td> 
>    <td align="center">759</td> 
>    <td align="left">Deep Learning API and Server in C++11 with Python bindings and support for Caffe.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/nivwusquorum/tensorflow-deepq" rel="nofollow">TensorFlow DeepQ</a></td> 
>    <td align="center">759</td> 
>    <td align="left">A deep Q learning demonstration using Google Tensorflow.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/yahoo/CaffeOnSpark" rel="nofollow">Caffe on Spark</a></td> 
>    <td align="center">724</td> 
>    <td align="left">Caffe On Spark.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/dnouri/nolearn" rel="nofollow">Nolearn</a></td> 
>    <td align="center">702</td> 
>    <td align="left">Abstractions around neural net libraries, most notably Lasagne.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/carpedm20/DCGAN-tensorflow" rel="nofollow">DCGAN TensorFlow</a></td> 
>    <td align="center">568</td> 
>    <td align="left">A tensorflow implementation of Deep Convolutional Generative Adversarial Networks</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/vlfeat/matconvnet" rel="nofollow">MatConvNet</a></td> 
>    <td align="center">479</td> 
>    <td align="left">MATLAB CNN toolbox for computer vision applications.</td> 
>   </tr> 
>   <tr> 
>    <td align="left"><a href="https://github.com/hughperkins/DeepCL" rel="nofollow">DeepCL</a></td> 
>    <td align="center">413</td> 
>    <td align="left">OpenCL library to train deep convolutional neural networks.</td> 
>   </tr> 
>  </tbody> 
> </table>

来源：[**Top Deep Learning Projects**][Top Deep Learning Projects]

[Top Deep Learning Projects]: https://github.com/aymericdamien/TopDeepLearning