嵌入式AI 双周简报 (2017-08-07)

业界新闻

• OpenCV 3.3版本发布

• [鱼和熊掌兼得，DNN加入 OpenCV 全家桶

  知乎专栏](https://zhuanlan.zhihu.com/p/28323601?utm_source=wechat_timeline&utm_medium=social&from=timeline)

• [Qualcomm Snapdragon Neural Processing Engine (NPE)

  Qualcomm Developer Network](https://developer.qualcomm.com/software/snapdragon-neural-processing-engine)

• [AI让芯片业洗牌: 苹果、微软和谷歌挤入赛道，英特尔、英伟达、高通、AMD几家欢乐几家愁

  新智元](http://mp.weixin.qq.com/s/WlZTXCRy0xGeuJLQMxZGeQ)

• [解密图森：英伟达为何投资这家无人车公司；估值18亿背后有位长者

  量子位](http://www.sohu.com/a/162189343_610300)

• [被英伟达相中，给Tier1供货，天瞳威视仅靠AI就搞定ADAS

  车东西](https://mp.weixin.qq.com/s?src=3&timestamp=1502018174&ver=1&signature=UozfhYMHOaRae6vesHbE0yvQl8DqpLOL5ru3ZXmsKHVAUaiot1ZdwO6KVmCEe7TVhPO1DlSEsgl-X8wwn95LDDoauBVGJIlk*DWEgLhmdZ5gddTV90tMZybHzU4iyJy7n3SZfs99YI4GewOq3LFpwPkrcGBIE20iavJ6jnDaM=)

• [ARM的最新NB-IoT报告

  5G](https://mp.weixin.qq.com/s?src=3&timestamp=1502018201&ver=1&signature=gUEmNUHy8y-SoCfrsriCmcDhzptEE4mc0M9tSLutgZ7ao2TvO25ZLK0iqVLspVKOADxdgPe3tu0IrjdlVtfx4aek4KEufToHuOAz2eXGro2OoeY8Yry0KfC47D8H8B0XiJvv-2G-PKJQN378zkUovM9LwC5SkxceA-8pa6t*-D4=)

• [ARM发飙！几个月后手机处理器将因它们而变天！

  智趣狗](https://mp.weixin.qq.com/s?__biz=MzI2NTM2OTc1Nw%3D%3D&mid=2247485358&idx=1&sn=1fb5f161cbf80093d952186dc5e8f02c&scene=45#wechat_redirect)

• [人工智能和云计算让芯片业洗牌，英特尔成了最大输家

  量子位](http://mp.weixin.qq.com/s/G_OEZJ0a62TZuMRq5jpXmA)

• [The Rise of AI Is Forcing Google and Microsoft to Become Chipmakers

  WIRED](https://www.wired.com/story/the-rise-of-ai-is-forcing-google-and-microsoft-to-become-chipmakers/)

• [如何评价腾讯刚出的ncnn库？

  知乎](https://www.zhihu.com/question/62871439)

• [沈向洋宣布微软开发 AI 芯片HPU，剑指英伟达等芯片巨头软肋

  新智元](http://www.sohu.com/a/160700395_473283)

• 超越GPU，FPGA、ASIC和更智能的手机 ｜ 新智元  
• “TensorFire - runs neural networks in the browser using WebGL” [Demo: style-transfer]

• [Getting Started with Neural Compute Stick and Rasbperry Pi 3

  YouTube](https://www.youtube.com/watch?v=f39NFuZAj6s)

论文/幻灯片

• [CVPR2017] Squeeze-and-Excitation networks (ILSVRC 2017 winner) at CVPR2017
• [1707.06990] Memory-Efficient Implementation of DenseNets
• BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
• Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing [code]
• [1704.06904] Residual Attention Network for Image Classification [code]
• [1707.09102] Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization
• [1708.00999] Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
• [1608.01409] Faster CNNs with Direct Sparse Convolutions and Guided Pruning
• [1606.05316] Learning Infinite-Layer Networks: Without the Kernel Trick
• [1707.09422] Hyperprofile-based Computation Offloading for Mobile Edge Networks
• [1705.04630] Forecasting using incomplete models
• [1707.09068] Tartan: Accelerating Fully-Connected and Convolutional Layers in Deep Learning Networks by Exploiting Numerical Precision Variability
• [1707.09926] A Framework for Super-Resolution of Scalable Video via Sparse Reconstruction of Residual Frames
• [1707.09855] Convolution with Logarithmic Filter Groups for Efficient Shallow CNN
• [1707.09597] ScanNet: A Fast and Dense Scanning Framework for Metastatic Breast Cancer Detection from Whole-Slide Images
• [ASPLOS’17] Neurosurgeon: Collaborative intelligence between the cloud and mobile edge
• [1604.08772] Towards Conceptual Compression
• [1608.02893] Syntactically Informed Text Compression with Recurrent Neural Networks
• [1608.05148] Full Resolution Image Compression with Recurrent Neural Networks
• [CVPR2017] Local Binary Convolutional Neural Networks [code]
• [1703.09746] Coordinating Filters for Faster Deep Neural Networks
• [1707.08005] Towards Evolutional Compression
• [ICML2017] Analytical Guarantees on Numerical Precision of Deep Neural Networks

开源项目

网络压缩

• yonghenglh6/DepthwiseConvolution: A personal mobile convolution implementation on caffe by liuhao.(only GPU)
• liuzhuang13/DenseNet: Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award)
• kevinzakka/DenseNet: PyTorch Implementation of “Densely Connected Convolutional Networks”
• hollance/MobileNet-CoreML: The MobileNet neural network using Apple’s new CoreML framework
• AngusG/tensorflow-xnor-bnn: BinaryNets in TensorFlow with XNOR GEMM op  
• jonathanmarek1/binarynet-tensorflow
• farmingyard/caffe-mobilenet: A caffe implementation of mobilenet’s depthwise convolution layer  
• kedartatwawadi/NN_compression
• chuanqi305/MobileNet-SSD: Caffe implementation of Google MobileNet SSD detection network, with pretrained weights on VOC0712 and mAP=0.727.

性能

• hollance/BNNS-vs-MPSCNN: Compares the speed of Apple’s two deep learning frameworks: BNNS and Metal Performance Shaders
• DeepMark/deepmark: THE Deep Learning Benchmarks

模型加密

• OpenMined/Syft: Homomorphically Encrypted Deep Learning Library

增强现实

• ProjectDent/ARKit-CoreLocation: Combines the high accuracy of AR with the scale of GPS data
• bjarnel/arkit-tictactoe: Tic-Tac-Toe implemented using ARKit+Scenekit
• arirawr/ARKit-FloorIsLava: Basic ARKit example that detects planes and makes them lava.
• exyte/ARTetris: Augmented Reality Tetris made with ARKit and SceneKit
• bjarnel/arkit-portal: Simple portal demo implemented with ARKit+SceneKit, the trick is to change the rendering order and render invisible “masks” to hide what’s inside.
• bjarnel/scenekit-tictactoe

安卓

• madeye/yolo-android: Quantized Tiny Yolo Demo on Android

iOS

• kingreza/SeeFood: Inspired by HBO’s Silicon Valley: SeeFood is an iOS app that uses CoreML to detect various dishes
• hollance/TensorFlow-iOS-Example: Source code for my blog post “Getting started with TensorFlow on iOS”
• Naituw/CoreMLDemo: Demo for CoreML & Vision Framework

模型应用

• msracver/FCIS: Fully Convolutional Instance-aware Semantic Segmentation
• bearpaw/PyraNet: Code for “Learning Feature Pyramids for Human Pose Estimation” (ICCV 2017)
• aquaviter/iot-demo-mxnet-greengrass
• bearpaw/PyraNet: Code for “Learning Feature Pyramids for Human Pose Estimation” (ICCV 2017)
• CongWeilin/mtcnn-caffe: Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks  
• foreverYoungGitHub/MTCNN: Repository for “Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Neural Networks”, implemented with Caffe, C++ interface.
• OAID/mtcnn: C++ project to implement MTCNN, a perfect face detect algorithm, on different DL frameworks. The most popular frameworks: caffe/mxnet/tensorflow, are all suppported now
• Seanlinx/mtcnn: this repository is the implementation of MTCNN in MXnet
• LaoDar/cnn_head_pose_estimator: a simple and fast mxnet version CNN based head pose estimator

加速库/框架　

• Darknet with NNPACK: NNPACK was used to optimize Darknet without using a GPU. It is useful for embedded devices using ARM CPUs  
• naibaf7/libdnn: Greentea LibDNN - a universal convolution implementation supporting CUDA and OpenCL
• blei-lab/edward: A library for probabilistic modeling, inference, and criticism. Deep generative models, variational inference. Runs on TensorFlow
• dmlc/nnvm-fusion: Kernel Fusion and Runtime Compilation Based on NNVM

音频图像视频处理

• MTG/essentia: C++ library for audio and music analysis, description and synthesis, including Python bindings
• Pili-完美直播体验（Pili Streaming Cloud）  
• pili-engineering/PLDroidMediaStreaming: PLDroidMediaStreaming 是 Pili 直播 SDK 的 Android 推流端，支持 RTMP 推流，h.264 和 AAC 编码，硬编、软编支持。具有丰富的数据和状态回调，方便用户根据自己的业务定制化开发。具有直播场景下的重要功能，如：美颜、背景音乐、水印等功能。PLDroidMediaStreaming 是现在目前重点维护的版本，自带采集模块也支持用户自己做采集端。
• pili-engineering/PLDroidShortVideo: PLDroidShortVideo 是七牛推出的一款适用于 Android 平台的短视频 SDK，提供了包括美颜、滤镜、水印、断点录制、分段回删、视频编辑、混音特效、本地/云端存储在内的多种功能，支持高度定制以及二次开发。
• pili-engineering/PLDroidPlayer: PLDroidPlayer 是 Pili 直播 SDK 的安卓播放器。支持所有直播常用的格式，如：RTMP、HLS、FLV。拥有优秀的功能和特性，如：首屏秒开、追帧优化、丰富的数据和状态回调、硬解软解支持。而且可以根据自己的业务进行高度定制化开发。
• pili-engineering/PLMediaStreamingKit: PLMediaStreamingKit 是 Pili 直播 SDK 的 iOS 推流端，支持 RTMP 推流，h.264 和 AAC 编码，硬编、软编支持。具有丰富的数据和状态回调，方便用户根据自己的业务定制化开发。具有直播场景下的重要功能，如：美颜、背景音乐、水印等功能。
• pili-engineering/PLShortVideoKit: PLShortVideoKit 是七牛推出的一款适用于 iOS 平台的短视频 SDK，提供了包括美颜、滤镜、水印、断点录制、分段回删、视频编辑、混音特效、本地/云端存储在内的多种功能，支持高度定制以及二次开发。
• pili-engineering/PLPlayerKit: PLPlayerKit 是 Pili 直播 SDK 的 iOS 播放器。支持所有直播常用的格式，如：RTMP、HLS、FLV。拥有优秀的功能和特性，如：首屏秒开、追帧优化、丰富的数据和状态回调、硬解软解支持。而且可以根据自己的业务进行高度定制化开发。
• pili-engineering/PLPlayerKit: PLPlayerKit 是 Pili 直播 SDK 的 iOS 播放器。支持所有直播常用的格式，如：RTMP、HLS、FLV。拥有优秀的功能和特性，如：首屏秒开、追帧优化、丰富的数据和状态回调、硬解软解支持。而且可以根据自己的业务进行高度定制化开发。

其它

• facebook/fb-caffe-exts: Some handy utility libraries and tools for the Caffe deep learning framework.
• Samsung/iotjs: Platform for Internet of Things with JavaScript code
• hollance/Forge: A neural network toolkit for Metal
• christopher5106/FastAnnotationTool: A tool using OpenCV to annotate images for image classification, optical character reading, etc.  
• raphui/rnk: rnk is a RTOS targeting ARM architecture.

数据集

• HandNet - A dataset of depth images of hands

博文/教程

• [Tutorial on Hardware Architectures for Deep Neural Networks

  MIT MICRO-50](http://eyeriss.mit.edu/tutorial.html)

• [基于mtcnn和facenet的实时人脸检测与识别系统开发

  知乎专栏](https://zhuanlan.zhihu.com/p/25025596?refer=shanren7)

• [Creating insanely fast image classifiers with MobileNet in TensorFlow

  HACKERNOON](https://hackernoon.com/creating-insanely-fast-image-classifiers-with-mobilenet-in-tensorflow-f030ce0a2991)

• [How to squeeze the most from your training data

  KDNUGGETS](http://www.kdnuggets.com/2017/07/squeeze-most-from-training-data.html)

• [Ubuntu16.04腾讯NCNN框架入门到应用

  CSDN](http://blog.csdn.net/Best_Coder/article/details/76201275)

• [Building Cross-Platform CUDA Applications with CMake

  NVIDIA](https://devblogs.nvidia.com/parallelforall/building-cuda-applications-cmake/?_lrsc=dca4b9d4-7747-48e0-b9a0-961aba39a657&ncid=so-twi-lt-799)

• [Caffe2 Bay Area Meetup (5/31/2017)

  YouTube](https://www.youtube.com/playlist?list=PLD5D5H5YL9SIjxj3IC019AprtgJAjIU3q)

Editor: 张先轶、袁帅

本作品采用知识共享署名-相同方式共享 2.0 通用许可协议进行许可。