README.md

   1 # NNtrainer
   2
   3 [![Code Coverage](http://nnsuite.mooo.com/nntrainer/ci/badge/codecoverage.svg)](http://nnsuite.mooo.com/nntrainer/ci/gcov_html/index.html)
   4 ![GitHub repo size](https://img.shields.io/github/repo-size/nnstreamer/nntrainer)
   5 ![GitHub issues](https://img.shields.io/github/issues/nnstreamer/nntrainer)
   6 ![GitHub pull requests](https://img.shields.io/github/issues-pr/nnstreamer/nntrainer)
   7 <a href="https://scan.coverity.com/projects/nnstreamer-nntrainer">
   8   <img alt="Coverity Scan Build Status"
   9        src="https://scan.coverity.com/projects/22512/badge.svg"/>
  10 </a>
  11 [![DailyBuild](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/daily_build_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/)
  12
  13 NNtrainer is a Software Framework for training Neural Network models on devices.
  14
  15 ## Overview
  16
  17 NNtrainer is an Open Source Project. The aim of the NNtrainer is to develop a Software Framework to train neural network models on embedded devices which have relatively limited resources. Rather than training whole layers of a network, NNtrainer trains only one or a few layers of the layers added after a feature extractor.
  18
  19 Even though NNTrainer can be used to train sub-models, it requires implementation of additional functionalities to train models obtained from other machine learning and deep learning libraries. In the current version, various machine learning algorithms such as k-Nearest Neighbor (k-NN), Neural Networks, Logistic Regression and Reinforcement Learning algorithms are implemented. We also provide examples for various tasks such as transfer learning of models. In some of these examples, deep learning models such as Mobilenet V2 trained with Tensorflow-lite, are used as feature extractors. All of these were tested on Galaxy S8 with Android and PC (Ubuntu 16.04).
  20
  21 ## Official Releases
  22
  23 |     | [Tizen](http://download.tizen.org/snapshots/tizen/unified/latest/repos/standard/packages/) | [Ubuntu](https://launchpad.net/~nnstreamer/+archive/ubuntu/ppa) | Android/NDK Build |
  24 | :-- | :--: | :--: | :--: |
  25 |     | 6.0M2 and later | 18.04 | 9/P |
  26 | arm | [![armv7l badge](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/armv7l_result_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/) | Available  | Ready |
  27 | arm64 |  [![aarch64 badge](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/aarch64_result_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/) | Available  | [![android badge](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/android_result_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/) |
  28 | x64 | [![x64 badge](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/x86_64_result_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/)  | [![ubuntu badge](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/ubuntu_result_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/)  | Ready  |
  29 | x86 | [![x86 badge](http://nnsuite.mooo.com/nntrainer/ci/daily-build/badge/i586_result_badge.svg)](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/)  | N/A  | N/A  |
  30 | Publish | [Tizen Repo](http://download.tizen.org/snapshots/tizen/unified/latest/repos/standard/packages/) | [PPA](https://launchpad.net/~nnstreamer/+archive/ubuntu/ppa) |   |
  31 | API | C (Official) | C/C++ | C/C++  |
  32
  33 - Ready: CI system ensures build-ability and unit-testing. Users may easily build and execute. However, we do not have automated release & deployment system for this instance.
  34 - Available: binary packages are released and deployed automatically and periodically along with CI tests.
  35 - [Daily Release](http://nnsuite.mooo.com/nntrainer/ci/daily-build/build_result/)
  36 - SDK Support: Tizen Studio (6.0 M2+)
  37
  38 ## Maintainer
  39 * [Jijoong Moon](https://github.com/jijoongmoon)
  40 * [MyungJoo Ham](https://github.com/myungjoo)
  41 * [Geunsik Lim](https://github.com/leemgs)
  42
  43 ## Reviewers
  44 * [Sangjung Woo](https://github.com/again4you)
  45 * [Wook Song](https://github.com/wooksong)
  46 * [Jaeyun Jung](https://github.com/jaeyun-jung)
  47 * [Hyoungjoo Ahn](https://github.com/helloahn)
  48 * [Parichay Kapoor](https://github.com/kparichay)
  49 * [Dongju Chae](https://github.com/dongju-chae)
  50 * [Gichan Jang](https://github.com/gichan-jang)
  51 * [Yongjoo Ahn](https://github.com/anyj0527)
  52 * [Jihoon Lee](https://github.com/zhoonit)
  53 * [Hyeonseok Lee](https://github.com/lhs8928)
  54 * [Mete Ozay](https://github.com/meteozay)
  55
  56 ## Components
  57
  58 ### Supported Layers
  59
  60 This component defines layers which consist of a neural network model. Layers have their own properties to be set.
  61
  62  | Keyword | Layer Name | Description |
  63  |:-------:|:---:|:---|
  64  |  conv2d | Convolution 2D |Convolution 2-Dimentional Layer |
  65  |  pooling2d | Pooling 2D |Pooling 2-Dimentional Layer. Support average / max / global average / global max pooing |
  66  | flatten | Flatten | Flatten Layer |
  67  | fully_connected | Fully Connected | Fully Connected Layer |
  68  | input | Input | Input Layer.  This is not always requied. |
  69  | batch_normalization | Batch Normalization Layer | Batch Normalization Layer. |
  70  | loss layer | loss layer | hidden from users |
  71  | activation | activaiton layer | set by layer property |
  72
  73 ### Supported Optimizers
  74
  75 NNTrainer Provides
  76
  77  | Keyword | Optimizer Name | Description |
  78  |:-------:|:---:|:---:|
  79  | sgd | Stochastic Gradient Decent | - |
  80  | adam | Adaptive Moment Estimation | - |
  81
  82 ### Supported Loss Functions
  83
  84 NNTrainer provides
  85
  86  | Keyword | Loss Name | Description |
  87  |:-------:|:---:|:---:|
  88  | mse | Mean squared Error | - |
  89  | cross | Cross Entropy - sigmoid | if activation last layer is sigmoid |
  90  | cross | Cross Entropy - softmax | if activation last layer is softmax |
  91
  92 ### Supported Activation Functions
  93
  94 NNTrainer provides
  95
  96  | Keyword | Loss Name | Description |
  97  |:-------:|:---:|:---|
  98  | tanh | tanh function | set as layer property |
  99  | sigmoid | sigmoid function | set as layer property |
 100  | relu | relu function | set as layer propery |
 101  | softmax | softmax function | set as layer propery |
 102  | weight_initializer | Weight Initialization | Xavier(Normal/Uniform), LeCun(Normal/Uniform),  HE(Normal/Unifor) |
 103  | weight_regularizer | weight decay ( L2Norm only ) | needs set weight_regularizer_param & type |
 104  | learnig_rate_decay | learning rate decay | need to set step |
 105
 106 ### Tensor
 107
 108 Tensor is responsible for calculation of a layer. It executes several operations such as addition, division, multiplication, dot production, data averaging and so on. In order to accelerate  calculation speed, CBLAS (C-Basic Linear Algebra: CPU) and CUBLAS (CUDA: Basic Linear Algebra) for PC (Especially NVIDIA GPU) are implemented for some of the operations. Later, these calculations will be optimized.
 109 Currently, we supports lazy calculation mode to reduce complexity for copying tensors during calculations.
 110
 111  | Keyword | Description |
 112  |:-------:|:---:|
 113  | 4D Tensor | B, C, H, W|
 114  | Add/sub/mul/div | - |
 115  | sum, average, argmax | - |
 116  | Dot, Transpose | - |
 117  | normalization, standardization | - |
 118  | save, read | - |
 119
 120 ### Others
 121
 122 NNTrainer provides
 123
 124  | Keyword | Loss Name | Description |
 125  |:-------:|:---:|:---|
 126  | weight_initializer | Weight Initialization | Xavier(Normal/Uniform), LeCun(Normal/Uniform),  HE(Normal/Unifor) |
 127  | weight_regularizer | weight decay ( L2Norm only ) | needs set weight_regularizer_constant & type |
 128  | learnig_rate_decay | learning rate decay | need to set step |
 129
 130 ### APIs
 131 Currently, we provide [C APIs](https://github.com/nnstreamer/nntrainer/blob/master/api/capi/include/nntrainer.h) for Tizen. C++ API will be also provided soon.
 132
 133
 134 ### Examples for NNTrainer
 135
 136 #### [Custom Shortcut Application](https://github.com/nnstreamer/nntrainer/tree/main/Applications/Tizen_native/CustomShortcut)
 137
 138
 139 A demo application which enable user defined custom shortcut on galaxy watch.
 140
 141 #### [MNIST Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/MNIST)
 142
 143 An example to train mnist dataset. It consists two convolution 2d layer, 2 pooling 2d layer, flatten layer and fully connected layer.
 144
 145 #### [Reinforcement Learning Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/ReinforcementLearning/DeepQ)
 146
 147 A reinforcement learning example with cartpole game. It is using DeepQ algorithm.
 148
 149 #### [Transfer Learning Examples](https://github.com/nnstreamer/nntrainer/tree/main/Applications/TransferLearning)
 150
 151 Transfer learning examples with for image classification using the Cifar 10 dataset and for OCR. TFlite is used for feature extractor and modify last layer (fully connected layer) of network.
 152
 153 #### ~Tizen CAPI Example~
 154
 155 An example to demonstrate c api for Tizen. It is same transfer learing but written with tizen c api.~
 156 Deleted instead moved to a [test](https://github.com/nnstreamer/nntrainer/blob/master/test/tizen_capi/unittest_tizen_capi.cpp)
 157
 158 #### [KNN Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/KNN)
 159
 160 A transfer learning example with for image classification using the Cifar 10 dataset. TFlite is used for feature extractor and compared with KNN.
 161
 162 #### [Logistic Regression Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/LogisticRegression)
 163
 164 A logistic regression example using NNTrainer.
 165
 166 ## [Getting Started](https://github.com/nnstreamer/nntrainer/blob/main/docs/getting-started.md)
 167
 168 Instructions for installing NNTrainer.
 169
 170 ### [Running Examples](https://github.com/nnstreamer/nntrainer/blob/main/docs/how-to-run-examples.md)
 171
 172 Instructions for preparing NNTrainer for execution
 173
 174 ## Open Source License
 175
 176 The nntrainer is an open source project released under the terms of the Apache License version 2.0.
 177
 178 ## Contributing
 179
 180 Contributions are welcome! Please see our [Contributing](https://github.com/nnstreamer/nntrainer/blob/main/docs/contributing.md) Guide for more details.
 181
 182 [![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/0)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/0)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/1)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/1)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/2)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/2)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/3)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/3)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/4)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/4)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/5)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/5)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/6)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/6)[![](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/images/7)](https://sourcerer.io/fame/dongju-chae/nnstreamer/nntrainer/links/7)