README.md
1<!--- Licensed to the Apache Software Foundation (ASF) under one -->
2<!--- or more contributor license agreements. See the NOTICE file -->
3<!--- distributed with this work for additional information -->
4<!--- regarding copyright ownership. The ASF licenses this file -->
5<!--- to you under the Apache License, Version 2.0 (the -->
6<!--- "License"); you may not use this file except in compliance -->
7<!--- with the License. You may obtain a copy of the License at -->
8
9<!--- http://www.apache.org/licenses/LICENSE-2.0 -->
10
11<!--- Unless required by applicable law or agreed to in writing, -->
12<!--- software distributed under the License is distributed on an -->
13<!--- "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY -->
14<!--- KIND, either express or implied. See the License for the -->
15<!--- specific language governing permissions and limitations -->
16<!--- under the License. -->
17
18# MXNet Examples
19
20This page contains a curated list of awesome MXNet examples, tutorials and blogs. It is inspired by [awesome-php](https://github.com/ziadoz/awesome-php) and [awesome-machine-learning](https://github.com/josephmisiti/awesome-machine-learning). See also [Awesome-MXNet](https://github.com/chinakook/Awesome-MXNet) for a similar list.
21
22 - [Contributing](#contributing)
23 - [List of examples](#list-of-examples)
24 - [Languages Binding Examples](#language-binding-examples)
25 - [Deep Learning Examples in the MXNet Project Repository](#deep-learning-examples-mxnet)
26 - [Other Deep Learning Examples with MXNet](#deep-learning-examples-other)
27 - [IPython Notebooks](#ipython-notebooks)
28 - [Mobile App Examples](#mobile-apps-examples)
29 - [Web Predictive Services](#web-predictive-services)
30 - [List of tutorials](#list-of-tutorials)
31 - [GPU Technology Conference 2016 Hands-on session](#gtc2016-hands-on)
32 - [Deep learning for hackers with MXnet](#deep-learning-for-hackers)
33 - [MXnet setup on AWS](#mxnet-aws)
34 - [Kaggle tutorials](#kaggle-tutorials)
35 - [Learning Note](#learning-note)
36 - [Machine Learning Challenge Winning Solutions](#winning-solutions)
37 - [Tools with MXnet](#tools-with-mxnet)
38
39## <a name="Contributing"></a>Contributing
40
41If you want to contribute to this list and the examples, please open a new pull request.
42
43
44### Examples
45
46Example applications or scripts should be submitted in this `example` folder.
47
48
49### Tutorials
50
51If you have a tutorial idea for the website, download the [Jupyter notebook tutorial template](https://github.com/apache/mxnet/tree/v1.x/example/MXNetTutorialTemplate.ipynb).
52
53#### Tutorial location
54
55Notebook tutorials should be submitted in the `docs/tutorials` folder, so that they maybe rendered in the [web site's tutorial section](https://mxnet.apache.org/tutorials/index.html).
56
57Do not forget to udpdate the `docs/tutorials/index.md` for your tutorial to show up on the website.
58
59#### Tutorial formatting
60
61The site expects the format to be markdown, so export your notebook as a .md via the Jupyter web interface menu (File > Download As > Markdown). Then, to enable the download notebook button in the web site's UI ([example](https://mxnet.apache.org/tutorials/python/linear-regression.html)), add the following as the last line of the file ([example](https://github.com/apache/incubator-mxnet/blame/master/docs/tutorials/python/linear-regression.md#L194)):
62
63```
64<!-- INSERT SOURCE DOWNLOAD BUTTONS -->
65```
66
67If you want some lines to show-up in the markdown but not in the generated notebooks, add this comment `<!--notebook-skip-line-->` after your ``. Like this:
68
69```
70<!--notebook-skip-line-->
71```
72
73Typically when you have a `plt.imshow()` you want the image tag `[png](img.png)` in the `.md` but not in the downloaded notebook as the user will re-generate the plot at run-time.
74
75#### Tutorial tests
76
77As part of making sure all our tutorials are running correctly with the latest version of MXNet, each tutorial is run automatically through a python2 and python3 jupyter notebook kernel in the CI, in a GPU environment, checking for errors and warnings.
78
79Add your own test here `tests/tutorials/test_tutorials.py`. (If you forget, don't worry your PR will not pass the sanity check).
80
81If your tutorial depends on specific packages, simply add them to this provisionning script: `ci/docker/install/ubuntu_tutorials.sh`
82
83## <a name="list-of-examples"></a>List of examples
84
85### <a name="language-binding-examples"></a>Languages Binding Examples
86------------------
87* [MXNet C++ API](https://mxnet.apache.org/api/c++/index.html)
88 - [C++ examples](https://github.com/apache/incubator-mxnet/tree/master/example/image-classification/predict-cpp) - Example code for using C++ interface, including NDArray, symbolic layer and models.
89* [MXNet Python API](https://mxnet.apache.org/api/python/index.html)
90* [MXNet Java API](https://mxnet.apache.org/api/java/index.html)
91* [MXNet Scala API](https://mxnet.apache.org/api/scala/index.html)
92* [MXNet R API](https://mxnet.apache.org/api/r/index.html)
93* [MXNet Julia API](https://mxnet.apache.org/api/julia/index.html)
94* [MXNet Perl API](https://mxnet.apache.org/api/perl/index.html)
95* [go-mxnet-predictor](https://github.com/songtianyi/go-mxnet-predictor) - Go binding for inference
96* [MXNet JNI](https://github.com/apache/mxnet/tree/v1.x/amalgamation/jni) - JNI(Android) library
97* [MXNet Amalgamation](https://github.com/apache/mxnet/tree/v1.x/amalgamation) - Amalgamation (entire library in a single file)
98* [MXNet Javascript](https://github.com/dmlc/mxnet.js/) - MXNetJS: Javascript Package for Deep Learning in Browser (without server)
99
100### <a name="deep-learning-examples-mxnet"></a>Deep Learning Examples in the MXNet Project Repository
101--------------
102* [Autoencoder](autoencoder) - unsupervised feature learning
103* [Bayesian Methods](bayesian-methods) - various examples related to Bayesian Methods
104* [Bidirectional LSTM Sorting](bi-lstm-sort) - use a bidirectional LSTM to sort an array
105* [Caffe](caffe) - how to call Caffe operators from MXNet
106* [CNN for Chinese Text Classification](cnn_chinese_text_classification) - a MXnet example for Chinese text classification
107* [CNN for Text Classification](cnn_text_classification) - a MXnet example for text classification
108* [CTC with MXNet](ctc) - a modification of warpctc
109* [Deep Embedded Clustering](deep-embedded-clustering) - unsupervised deep embedding for clustering analysis
110* [Dense-Sparse-Dense Training](dsd) - Dense-Sparse-Dense Training for deep neural networks
111* [Fully Convolutional Networks](fcn-xs) - fully convolutional networks for semantic segmentation
112* [Generative Adversarial Networks with R](gan/CGAN_mnist_R) - GAN examples in R
113* [Gluon Examples](gluon) - several examples using the Gluon API
114 * [Style Transfer](gluon/style_transfer) - a style transfer example using gluon
115 * [Word Language Model](gluon/word_language_model) - an example that trains a multi-layer RNN on the Penn Treebank language modeling benchmark
116 * [SN-GAN](gluon/sn_gan) - an example that utilizes spectral normalization to train GAN(Generative adversarial network) using Gluon API
117* [Image Classification with R](image-classification) - image classification on MNIST,CIFAR,ImageNet-1k,ImageNet-Full, with multiple GPU and distributed training.
118* [Kaggle 1st national data science bowl](kaggle-ndsb1) - a MXnet example for Kaggle Nation Data Science Bowl 1
119* [Kaggle 2nd national data science bowl](kaggle-ndsb2) - a tutorial for Kaggle Second Nation Data Science Bowl
120* [Memory Cost](memcost) - a script to show the memory cost of different allocation strategies
121* [Model Parallelism](model-parallel) - various model parallelism examples
122 * [Model Parallelism with LSTM](model-parallel/lstm) - an example showing how to do model parallelism with a LSTM
123 * [Model Parallelism with Matrix Factorization](model-parallel/lstm) - a matrix factorization algorithm for recommendations
124* [Module API](module) - examples with the Python Module API
125* [Multi-task Learning](multi-task) - how to use MXNet for multi-task learning
126* [MXNet Adversarial Variational Autoencoder](mxnet_adversarial_vae) - combines a variational autoencoder with a generative adversarial network
127* [Noise-contrastive estimation loss](nce-loss) - used to speedup multi-class classification
128* [Neural Style](neural-style) - use deep learning for style transfer in images
129* [Numpy Operator Customization](numpy-ops) - Examplea on quick customize new ops with Numpy
130* [Profiling](profiler) - generate profiling results in json files
131* [Quantization and Calibration Examples](quantization) - examples of quantizing a FP32 model to INT8 and performing low-precision inference with Intel MKL-DNN on CPU or cuDNN on GPU
132* [R-CNN](rcnn) - R-CNN with distributed implementation and data parallelization
133* [Recommender Systems](recommenders) - examples of how to build various kinds of recommender systems
134* [Reinforcement Learning](reinforcement-learning) - a variety of reinforcement learning examples
135 * [A3C](reinforcement-learning/a3c)
136 * [DDPG](reinforcement-learning/ddpg) - example of training DDPG for CartPole
137 * [DQN](reinforcement-learning/dqn) - examples of training DQN and Double DQN to play Atari Games
138 * [Parallel Advantage-Actor Critic](reinforcement-learning/parallel_actor_critic)
139* [Restricted Boltzmann Machine](restricted-boltzmann-machine) - an example of the binary restricted Boltzmann machine learning MNIST
140* [RNN Time Major](rnn-time-major) - RNN implementation with Time-major layout
141* [Recurrent Neural Net](rnn) - creating recurrent neural networks models using high level `mxnet.rnn` interface
142* [Sparse](sparse) - a variety of sparse examples
143 * [Factorization Machine](sparse/factorization_machine)
144 * [Linear Classification](sparse/linear_classification)
145 * [Matrix Factorization](sparse/matrix_factorization)
146 * [Wide Deep](sparse/wide_deep)
147* [Single Shot MultiBox Detector](ssd) - SSD object recognition example
148* [Stochastic Depth](stochastic-depth) - implementation of the stochastic depth algorithm
149* [Support Vector Machine](svm_mnist) - an SVM example using MNIST
150* [Variational Auto Encoder](vae) - implements the Variational Auto Encoder in MXNet using MNIST
151
152### <a name="deep-learning-examples-other"></a>Other Deep Learning Examples with MXNet
153
154* [Face Recognition with ArcFace](https://github.com/onnx/models/tree/master/vision/body_analysis/arcface) - ONNX model for face recognition with notebooks for training, validating and running inference in MXNet by [abhinavs95](https://github.com/abhinavs95)
155* [Chinese plate recognition](https://github.com/imistyrain/mxnet-mr) - Recognize Chinese vehicle plate, by [imistyrain](https://github.com/imistyrain)
156* [Fast R-CNN](https://github.com/precedenceguo/mx-rcnn) by [Jian Guo](https://github.com/precedenceguo)
157* "End2End Captcha Recognition (OCR)" by [xlvector](https://github.com/xlvector) [github link](https://github.com/xlvector/learning-dl/tree/master/mxnet/ocr) [Blog in Chinese](http://blog.xlvector.net/2016-05/mxnet-ocr-cnn/)
158* "Prediction step of xlvector's lstm ocr" by [melody-rain](https://github.com/melody-rain) [github link](https://github.com/melody-rain/mxnet/commit/46002e31fc34c746c01bcaa7ade999187068ad3c) [Blog in Chinese](https://zhuanlan.zhihu.com/p/22698511)
159* "Solving classification + regression with MXnet in Multi Input + Multi Obj" by [xlvector](https://github.com/xlvector) [github link](https://gist.github.com/xlvector/c304d74f9dd6a3b68a3387985482baac) [Blog in Chinese](http://blog.xlvector.net/2016-05/mxnet-regression-classification-for-concret-continuous-features/)
160* "Learn to sort by LSTM" by [xlvector](https://github.com/xlvector) [github link](https://github.com/xlvector/learning-dl/tree/master/mxnet/lstm_sort) [Blog in Chinese](http://blog.xlvector.net/2016-05/mxnet-lstm-example/)
161* [Neural Art using extremely lightweight (<500K) neural network](https://github.com/pavelgonchar/neural-art-mini) Lightweight version of mxnet neural art implementation by [Pavel Gonchar](https://github.com/pavelgonchar)
162* [Neural Art with generative networks](https://github.com/zhaw/neural_style) by [zhaw](https://github.com/zhaw)
163* [Faster R-CNN in MXNet with distributed implementation and data parallelization](https://github.com/apache/mxnet/tree/v1.x/example/rcnn)
164* [Asynchronous Methods for Deep Reinforcement Learning in MXNet](https://github.com/zmonoid/Asyn-RL-MXNet/blob/master/mx_asyn.py) by [zmonoid](https://github.com/zmonoid)
165* [Deep Q-learning in MXNet](https://github.com/zmonoid/DQN-MXNet) by [zmonoid](https://github.com/zmonoid)
166* [Face Detection with End-to-End Integration of a ConvNet and a 3D Model (ECCV16)](https://github.com/tfwu/FaceDetection-ConvNet-3D) by [tfwu](https://github.com/tfwu), source code for paper Yunzhu Li, Benyuan Sun, Tianfu Wu and Yizhou Wang, "Face Detection with End-to-End Integration of a ConvNet and a 3D Model", ECCV 2016 <https://arxiv.org/abs/1606.00850>
167* [End-to-End Chinese plate recognition base on MXNet](https://github.com/szad670401/end-to-end-for-chinese-plate-recognition) by [szad670401](https://github.com/szad670401)
168* [Reproduce ResNet-v2 (Identity Mappings in Deep Residual Networks) using MXNet](https://github.com/tornadomeet/ResNet) by [tornadomeet](https://github.com/tornadomeet)
169* [Learning similarity among images in MXNet](http://www.jianshu.com/p/70a66c8f73d3) by xlvector in Chinese. Github [link](https://github.com/xlvector/learning-dl/tree/master/mxnet/triple-loss)
170* [Matrix decomposition (SVD) with MXNet](http://www.jianshu.com/p/ebf7bf53ed3e) by xlvector in Chinese. Github [link](https://github.com/xlvector/mxnet/blob/svd/example/svd/svd.py)
171* [MultiGPU enabled image generative models (GAN and DCGAN)](https://github.com/tqchen/mxnet-gan) by [Tianqi Chen](https://github.com/tqchen)
172* [Deep reinforcement learning for playing flappybird by mxnet](https://github.com/li-haoran/DRL-FlappyBird) by LIHaoran
173* [Neural Style in Markov Random Field (MRF) and Perceptual Losses Realtime transfer](https://github.com/zhaw/neural_style) by [zhaw](https://github.com/zhaw)
174* [MTCNN Face keypoints detection and alignment](https://github.com/YYuanAnyVision/mxnet_mtcnn_face_detection) by [yuanyang](https://github.com/YYuanAnyVision), source code for [paper](https://kpzhang93.github.io/papers/spl.pdf) "Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks", [Kaipeng Zhang](https://github.com/kpzhang93), Zhanpeng Zhang, Zhifeng Li and Yu Qiao, IEEE Signal Processing Letters, 23(10), 2016
175* [SSD: Single Shot MultiBox Object Detector](https://github.com/zhreshold/mxnet-ssd) by [zhreshold](https://github.com/zhreshold)
176* [Fast Neural Style in Scala](https://github.com/Ldpe2G/DeepLearningForFun/tree/master/Mxnet-Scala/FastNeuralStyle) by [Ldpe2G](https://github.com/Ldpe2G)
177* [LSTM Human Activity Recognition](https://github.com/Ldpe2G/DeepLearningForFun/tree/master/Mxnet-Scala/HumanActivityRecognition) by [Ldpe2G](https://github.com/Ldpe2G)
178* [Visual Question Answering](https://github.com/liuzhi136/Visual-Question-Answering) by [liuzhi136](https://github.com/liuzhi136)
179* [Deformable ConvNets](https://arxiv.org/abs/1703.06211) ([github](https://github.com/msracver/Deformable-ConvNets)) by [MSRACVer](https://github.com/msracver)
180* [OCR with bi-LSTM and CTC Loss in Gluon](https://github.com/ThomasDelteil/Gluon_OCR_LSTM_CTC) by [ThomasDelteil](https://github.com/ThomasDelteil)
181* [Visual Search with Gluon and HNSWlib](https://github.com/ThomasDelteil/VisualSearch_MXNet), by [ThomasDelteil](https://github.com/ThomasDelteil), online demo [here](https://thomasdelteil.github.io/VisualSearch_MXNet/)
182* [MXNet-face](https://github.com/tornadomeet/mxnet-face) - Using MXNet for a face-related algorithm by [tornadomeet](https://github.com/tornadomeet) where the single model gets 97.13%+-0.88% accuracy on LFW, and with only 20MB size
183
184### <a name="ipython-notebooks"></a>IPython Notebooks
185-----------------
186* [Predict with Pre-trained model](https://github.com/dmlc/mxnet-notebooks/blob/master/python/moved-from-mxnet/predict-with-pretrained-model.ipynb) - Notebook on how to predict with pretrained model.
187* [composite symbol](https://github.com/dmlc/mxnet-notebooks/blob/master/python/moved-from-mxnet/composite_symbol.ipynb) - A demo of how to composite a symbolic Inception-BatchNorm Network
188* [cifar-10 recipe](https://github.com/dmlc/mxnet-notebooks/blob/master/python/moved-from-mxnet/cifar10-recipe.ipynb) - A step by step demo of how to use MXNet
189* [cifar-100](https://github.com/dmlc/mxnet-notebooks/blob/master/python/moved-from-mxnet/cifar-100.ipynb) - A demo of how to train a 75.68% accuracy CIFAR-100 model
190* [simple bind](https://github.com/dmlc/mxnet-notebooks/blob/master/python/moved-from-mxnet/simple_bind.ipynb) - A demo of low level training API.
191* [Multi task tutorial](https://github.com/haria/mxnet-multi-task-example/blob/master/multi-task.ipynb) - A demo of how to train and predict multi-task network on both MNIST and your own dataset.
192* [class active maps](https://github.com/dmlc/mxnet-notebooks/blob/master/python/moved-from-mxnet/class_active_maps.ipynb) - A demo of how to localize the discriminative regions in an image using global average pooling (GAP) in CNNs.
193* [DMLC MXNet Notebooks](https://github.com/dmlc/mxnet-notebooks) DMLC's repo for various notebooks ranging from basic usages of MXNet to state-of-the-art deep learning applications.
194* [AWS Seoul Summit 2017 Demos](https://github.com/sxjscience/aws-summit-2017-seoul) The demo codes and ipython notebooks in AWS Seoul Summit 2017.
195* [Character-level CNN for text classification](https://github.com/ThomasDelteil/CNN_NLP_MXNet) Performing category classification on Amazon reviews using Gluon and character-level Convolutional Neural Networks. Online demo [here](https://thomasdelteil.github.io/CNN_NLP_MXNet/)
196
197### <a name="mobile-apps-examples"></a>Mobile App Examples
198-------------------
199* [MXNet Android Classification App](https://github.com/Leliana/WhatsThis) - Image classification on Android with MXNet.
200* [MXNet iOS Classification App](https://github.com/pppoe/WhatsThis-iOS) - Image classification on iOS with MXNet.
201* [Compile MXnet on Xcode (in Chinese)](http://www.liuxiao.org/2015/12/ios-mxnet-%E7%9A%84-ios-%E7%89%88%E6%9C%AC%E7%BC%96%E8%AF%91/) - a step-by-step tutorial of compiling MXnet on Xcode for iOS app
202
203### <a name="web-predictive-services"></a>Web Predictive Services
204-----------------------
205* [MXNet Shinny](https://github.com/thirdwing/mxnet_shiny) - Source code for quickly creating a Shiny R app to host online image classification.
206* [Machine Eye](http://rupeshs.github.io/machineye/) - Web service for local image file/image URL classification without uploading.
207
208## <a name="list-of-tutorials"></a>List of tutorials
209
210### <a name="gtc2016-hands-on"></a>GPU Technology Conference 2016 Hands-on session
211
212* [Video on GTC 2016 site](http://on-demand.gputechconf.com/gtc/2016/video/L6143.html)
213* [Video backup in Mainland China](http://pan.baidu.com/s/1eS58Gue)
214* [iPython Notebook](https://github.com/dmlc/mxnet-gtc-tutorial)
215
216### <a name="deep-learning-for-hackers"></a>Deep learning for hackers with MXNet
217
218* Deep learning for hackers with MXNet (1) GPU installation and MNIST [English](https://no2147483647.wordpress.com/2015/12/07/deep-learning-for-hackers-with-mxnet-1/) [Chinese](http://phunter.farbox.com/post/mxnet-tutorial1) - a tutorial of installing MXnet with GPU and introduction to deep learning by MNIST example.
219* Deep learning for hackers with MXNet (2): Neural art [English](https://no2147483647.wordpress.com/2015/12/21/deep-learning-for-hackers-with-mxnet-2/) [Chinese](http://phunter.farbox.com/post/mxnet-tutorial2) - a tutorial of generating Van Gogh style cat paintings.
220
221### <a name="mxnet-aws"></a>MXNet on the cloud
222* [Setup Amazon AWS GPU instance with MXnet](https://no2147483647.wordpress.com/2016/01/16/setup-amazon-aws-gpu-instance-with-mxnet/) - AWS GPU instance setup with GPU (CUDA with latest cuDNN and S3 support)
223* [Intro Guide to AWS (MXNet with Julia)](http://www.datasciencebowl.com/aws_guide/) - A step-by-step guide of using spot instances with Amazon Web Services (AWS) to help you save money when training DSB models on MXNet by [Mike Kim](http://www.datasciencebowl.com/author/mikekim/)
224* [Building Deep Neural Networks in the Cloud with Azure GPU VMs, MXNet and Microsoft R Server](https://blogs.technet.microsoft.com/machinelearning/2016/09/15/building-deep-neural-networks-in-the-cloud-with-azure-gpu-vms-mxnet-and-microsoft-r-server/) by [Cortana Intelligence and ML Blog Team](https://social.technet.microsoft.com/profile/Cortana+Intelligence+and+ML+Blog+Team) at Microsoft
225* [Applying Deep Learning at Cloud Scale, with Microsoft R Server & Azure Data Lake](https://blogs.technet.microsoft.com/machinelearning/2016/10/31/applying-cloud-deep-learning-at-scale-with-microsoft-r-server-azure-data-lake/) by [Cortana Intelligence and ML Blog Team](https://social.technet.microsoft.com/profile/Cortana+Intelligence+and+ML+Blog+Team) at Microsoft
226* [Training Deep Neural Neural Networks on ImageNet Using Microsoft R Server and Azure GPU VMs](https://blogs.technet.microsoft.com/machinelearning/2016/11/15/imagenet-deep-neural-network-training-using-microsoft-r-server-and-azure-gpu-vms/) by [Cortana Intelligence and ML Blog Team](https://social.technet.microsoft.com/profile/Cortana+Intelligence+and+ML+Blog+Team) at Microsoft
227* [Cloud-Scale Text Classification with Convolutional Neural Networks on Microsoft Azure](https://blogs.technet.microsoft.com/machinelearning/2017/02/13/cloud-scale-text-classification-with-convolutional-neural-networks-on-microsoft-azure/) by [Cortana Intelligence and ML Blog Team](https://social.technet.microsoft.com/profile/Cortana+Intelligence+and+ML+Blog+Team) at Microsoft
228* [Distributed Deep Learning Made Easy](https://aws.amazon.com/blogs/compute/distributed-deep-learning-made-easy/) at AWS/Amazon for deploying deep learning clusters using MXNet
229
230### <a name="kaggle-tutorials"></a>Kaggle tutorials
231* [Kaggle 2nd Annual Data Science Bowl End-to-End Deep Learning Tutorial (Python)](https://www.kaggle.com/c/second-annual-data-science-bowl/forums/t/18079/end-to-end-deep-learning-tutorial-0-0392) - an end-to-end python tutorial for Kaggle heart disease diagnose competition (public leaderboard score 0.0392)
232* [Kaggle 2nd Annual Data Science Bowl End-to-End Deep Learning Tutorial (R)](https://www.kaggle.com/c/second-annual-data-science-bowl/forums/t/18122/deep-learning-model-in-r) - an end-to-end R tutorial for Kaggle heart disease diagnose competition
233* [Dogs vs. Cats classification with mxnet and R](https://statist-bhfz.github.io/cats_dogs_finetune) - end-to-end (not winning) tutorial with an example of fine-tuning in R
234
235### <a name="learning-note"></a>Learning Note
236* [Learning Note in Chinese](https://github.com/zhubuntu/MXNet-Learning-Note) - MXNet learning note in Chinese.
237* [Getting Started with MXNet](https://indico.io/blog/getting-started-with-mxnet/) by [indico.io](https://indico.io) (Chinese Translation [MXNet实践](http://www.infoq.com/cn/articles/practise-of-mxnet) by [侠天](http://www.infoq.com/cn/author/%E4%BE%A0%E5%A4%A9) )
238* [{mxnet} R package from MXnet, an intuitive Deep Learning framework including CNN & RNN](http://tjo-en.hatenablog.com/entry/2016/03/30/233848) by [TJO](http://tjo-en.hatenablog.com/)
239* [MXnet with R: combined power of deep learning](http://cos.name/2016/04/mxnet-r/) in Chinese by Tong He
240* [Understand MXNet dependency engine](http://yuyang0.github.io/articles/mxnet-engine.html) in Chinese by [Yu Yang](https://github.com/yuyang0)
241
242## <a name="winning-solutions"></a>Machine Learning Challenge Winning Solutions
243
244* Dmitrii Tsybulevskii, 1st place of the [Yelp Restaurant Photo Classification](https://www.kaggle.com/c/yelp-restaurant-photo-classification). Link to [the Kaggle interview](http://blog.kaggle.com/2016/04/28/yelp-restaurant-photo-classification-winners-interview-1st-place-dmitrii-tsybulevskii/).
245
246## <a name="tools-with-mxnet"></a>Tools with MXnet
247* [TensorFuse](https://github.com/dementrock/tensorfuse) - Common interface for Theano, CGT, TensorFlow, and mxnet (experimental) by [dementrock](https://github.com/dementrock)
248* [MXnet-face](https://github.com/tornadomeet/mxnet-face) - Using mxnet for face-related algorithm by [tornadomeet](https://github.com/tornadomeet) where the single model get 97.13%+-0.88% accuracy on LFW, and with only 20MB size.
249* [MinPy](https://github.com/dmlc/minpy) - Pure numpy practice with third party operator Integration and MXnet as backend for GPU computing
250* [MXNet Model Server](https://github.com/awslabs/mxnet-model-server) - a flexible and easy to use tool for serving Deep Learning models
251
