Jetson平台使用Inter 神经网络计算棒

Jetson平台使用Inter 神经网络计算棒(Neural Compute Stick, NCS)

工作方式#

NCS工作方式分为两种,一种是在主机上将训练好的模型生成NCS可执行graph文件,该文件用于推理过程;另一种是在树莓派、Jetson TX2等便携式计算机上加速推理过程。

主机端使用NCS#

安装#

将神经计算棒插入主机中,在终端执行以下命令:

Copy
git clone https://github.com/movidius/ncsdk cd ncsdk make install

make install的作用如下:

  • 检查安装Tensorflow;

  • 检查安装Caffe(SSD-caffe);

  • 编译安装ncsdk(不包含inference模块,只包含mvNCCompile相关模块,用来将Caffe或Tensorflow模型转成NCS graph的)

之后执行:

Copy
make example

程序顺利运行不报错的话,就说明已经安装成功了。

使用#

将训练好的模型生成NCS可以执行的graph文件,在终端执行以下命令:

Copy
mvNCCompile network.prototxt -w network.caffemodel -s MaxNumberOfShaves -in InputNodeName -on OutputNodeName-is InputWidth InputHeight -o OutputGraphFilename

network.prototxt:.prototxt文件的路径
-w network.caffemode:模型文件的路径
-s MaxNumberOfShaves:1, 2, 4, 8, 12。默认为12
-in InputNodeName:选择指定一个特定的输入图层(它将匹配prototxt文件中的名称,可选项)
-on OutputNodeName:默认情况下网络是通过输出张量进行处理的,这个选项允许用户在网络中选择一个替代端点(可选项)
-is InputWidth InputHeight:输入尺寸,需要与网络匹配
-o OutputGraphFilename:生成的graph文件存储路径

在Jetson TX2上安装NCS#

在TX2上只完成推理(Inference)过程,所以只需安装API-only模式即可,将NCS插入到TX2上。

安装依赖#

Copy
sudo apt-get install -y libusb-1.0-0-dev libprotobuf-dev libleveldb-dev libsnappy-dev libopencv-dev libhdf5-serial-dev protobuf-compiler libatlas-base-dev git automake byacc lsb-release cmake libgflags-dev libgoogle-glog-dev liblmdb-dev swig3.0 graphviz libxslt-dev libxml2-dev gfortran python3-dev python-pip python3-pip python3-setuptools python3-markdown python3-pillow python3-yaml python3-pygraphviz python3-h5py python3-nose python3-lxml python3-matplotlib python3-numpy python3-protobuf python3-dateutil python3-skimage python3-scipy python3-six python3-networkx python3-tk

下载源码#

Copy
mkdir ~/workspace cd ~/workspace git clone https://github.com/movidius/ncsdk

编译和安装NCSDK API框架#

Copy
cd ~/workspace/ncsdk/api/src make sudo make install

测试#

Copy
cd ~/workspace git clone https://github.com/movidius/ncappzoo cd ncappzoo/apps/hello_ncs_py python3 hello_ncs.py

出现以下结果:

Copy
Hello NCS! Device opened normally. Goodbye NCS! Device closed normally. NCS device working.

API-only模式安装成功。

TX2利用NCS加速推理使用#

参数预定义:

  • GRAPH_PATH:graph文件路径;
  • IMAGE_PATH:要分类的图片的路径;
  • IMAGE_DIM:由选择的神经网络定义的图像尺寸;例:GoogLeNet uses 224x224 pixels, AlexNet uses 227x227 pixels
  • IMAGE_STDDEV:由选择的神经网络定义的标准差(标度值);例:GoogLeNet uses no scaling factor, InceptionV3 uses 128 (stddev = 1/128)
  • IMAGE_MEAN:平均减法是深度学习中常用的一种技术,用于对数据进行中心处理。例:ILSVRC dataset, the mean is B = 102 Green = 117 Red = 123

使用NCS做图像分类的5个步骤:#

从mvnc库中引入mvncapi模块

Copy
import mvnc.mvncapi as mvnc

01#

将NCS插入应用处理器(Ubuntu笔记本电脑/台式机)USB端口时,它将自身列为USB设备。通过调用API来查找枚举的NCS设备:

Copy
# Look for enumerated Intel Movidius NCS device(s); quit program if none found. devices = mvnc.EnumerateDevices() if len( devices ) == 0: print( 'No devices found' ) quit()

如果插入了多个NCS,还需要选择一个NCS并打开:

Copy
# Get a handle to the first enumerated device and open it device = mvnc.Device( devices[0] ) device.OpenDevice()

02#

加载graph文件到NCS

Copy
# Read the graph file into a buffer with open( GRAPH_PATH, mode='rb' ) as f: blob = f.read() # Load the graph buffer into the NCS graph = device.AllocateGraph( blob )

03#

将图像加载到Intel Movidius NCS上以运行推理

图像预处理:
1.调整图像大小/裁剪图像以匹配预先训练的网络定义的尺寸。例:GoogLeNet uses 224x224 pixels, AlexNet uses 227x227 pixels.
2.每个通道的平均值(蓝色,绿色和红色)从整个数据集中减去。这是深度学习中常用的一种技术,可以集中数据。
3.将图像转换为半精度浮点数(fp16)数组(NCS输入数据格式为fp16),并使用LoadTensor函数调用将图像加载到NCS上。skimage库可以在一行代码中完成此操作。

Copy
# Read & resize image (Image size is defined during training) img = print_img = skimage.io.imread( IMAGES_PATH ) img = skimage.transform.resize( img, IMAGE_DIM, preserve_range=True ) # Convert RGB to BGR [skimage reads image in RGB, but Caffe uses BGR] img = img[:, :, ::-1] # Mean subtraction & scaling [A common technique used to center the data] img = img.astype( numpy.float32 ) img = ( img - IMAGE_MEAN ) * IMAGE_STDDEV # Load the image as a half-precision floating point array graph.LoadTensor( img.astype( numpy.float16 ), 'user object' )

04#

从NCS读取并打印推理结果

Copy
# Get the results from NCS output, userobj = graph.GetResult() # Print the results print('\n------- predictions --------') labels = numpy.loadtxt( LABELS_FILE_PATH, str, delimiter = '\t' ) order = output.argsort()[::-1][:6] for i in range( 0, 5 ): print ('prediction ' + str(i) + ' is ' + labels[order[i]]) # Display the image on which inference was performed skimage.io.imshow( IMAGES_PATH ) skimage.io.show( )

05#

卸载图形并关闭设备

为了避免内存泄漏和/或分段错误,我们应该关闭所有打开的文件或资源并释放所有使用的内存。

Copy
graph.DeallocateGraph() device.CloseDevice()

运行Demo

Demo采用Adrian Rosebrock博客Real-time object detection on the Raspberry Pi with the Movidius NCS - PyImageSearch里的程序(https://www.pyimagesearch.com/2018/02/19/real-time-object-detection-on-the-raspberry-pi-with-the-movidius-ncs/),这个程序基于Mobilenet-ssd模型对视频流做实时检测,如图2所示,Demo采用USB摄像头读取实时视频。图3为检测结果。

参考#

https://github.com/movidius/ncsdk

https://movidius.github.io/blog/ncs-apps-on-rpi/

https://movidius.github.io/blog/ncs-image-classifier/

https://www.pyimagesearch.com/2018/02/19/real-time-object-detection-on-the-raspberry-pi-with-the-movidius-ncs/

posted @   nanmi  阅读(512)  评论(1编辑  收藏  举报
点击右上角即可分享
微信分享提示
CONTENTS