# OpenVINO Quick Get Started on Windows 10

###### tags: `OpenVINO` `2021.2` `Windows 10`

## 在 Windows 10 電腦上安裝 OpenVINO Toolkit 2021.2

### 2021.3. Please go to https://hackmd.io/SeCuh4DxTFGt3Vt3rPFlTQ

- Table of Content
[ToC]

### :memo: 系統需求

硬體 :
Intel CPU 筆電/桌機/NUC 

軟體 :
Microsoft Windows 10
Intel DistributionOpenVINO Toolkit
Python 3.7.9 64-bit


### 下載 Intel® Distribution of OpenVINO™ Toolkit
https://software.intel.com/en-us/openvino-toolkit/choose-download


### 安裝 Intel® Distribution of OpenVINO™ Toolkit





### 下載並安裝Python 3.7.9
https://www.python.org/downloads/windows/




### 安裝OpenVINO toolkit所需的Python套件

"c:\Program Files (x86)\Intel\openvino_2021.2.185\bin\setupvars.bat"
cd "C:\ProgramProgram Files (x86)\intel\openvino_2021.2.185\deployment_tools\model_optimizer\install_prerequisites"
install_prerequisites_tf2.bat
install_prerequisites_onnx.bat
cd "c:\Program Files (x86)\intel\openvino_2021.2.185\deployment_tools\tools\model_downloader\"
pip install -r requirements.in

### 安裝OpenVINO toolkit所需的Python套件 : 使用virtualenv (建議使用,非必須)

python -m venv c:\Users\Public\ov_venv
c:\Users\Public\ov_venv\Scripts\activate
"c:\Program Files (x86)\Intel\openvino_2021.2.185\bin\setupvars.bat"
pip install -r "C:\Program Files (x86)\intel\openvino_2021.2.185\deployment_tools\model_optimizer\requirements_tf2.txt
pip install -r "C:\Program Files (x86)\intel\openvino_2021.2.185\deployment_tools\model_optimizer\requirements_onnx.txt
cd "c:\Program Files (x86)\intel\openvino_2021.2.185\deployment_tools\tools\model_downloader\"
pip install -r requirements.in

### 使用OpenVINO Toolkit做影像辨識

使用神經網路模型執行影像辨識只要三個步驟
1. 取得神經網路模型
1. 對神經網路模型進行推論優化
1. 執行影像辨識推論 (在Intel CPU, Intel GPU以及VPU)

### 步驟1 取得神經網路模型


### 步驟2 對神經網路模型進行推論優化


### 步驟3 執行影像辨識推論 (18 lines of Python code)


### car.png 可以在C:\Program Files (x86)\Intel\openvino_2021.3.394\deployment_tools\demo\找到.

import cv2
import numpy as np
from openvino.inference_engine import IENetwork, IECore
ie = IECore()
net = ie.read_network(model='mobilenet-v2-1.0-224.xml')
input_blob = next(iter(net.inputs))
out_blob = next(iter(net.outputs))
batch,channel,height,width  = net.inputs[input_blob].shape
image = cv2.imread('car.png')
cv2.imshow("input", image)
image = cv2.resize(image, (width, height))
image = image.transpose((2, 0, 1))  # Change data layout from HWC to CHW
exec_net = ie.load_network(network=net, device_name='CPU')
res = exec_net.infer(inputs={input_blob: image})
idx = np.argsort(np.squeeze(res[out_blob][0]))[::-1]
for i in range(5):
    print(idx[i]+1, res[out_blob][0][idx[i]])
cv2.waitKey(3*1000)

### 安裝Visual Studio Community 2019 (非必須)
(Accuracy Checker 以及 Post-Training Optimization Tool (POT) 會使用到VS 2019)

pip install cmake
Download Visual Studio Community version, https://visualstudio.microsoft.com/zh-hant/vs/express/
只需安裝