# 安裝 OpenCV (Ubuntu 16.04) > [轉載網址](https://askubuntu.com/questions/783956/how-to-install-opencv-3-1-for-python-3-5-on-ubuntu-16-04-lts) > [name=謝朋諺] ###### tags: `Environment` 現在只要這樣安裝就可以了！ ``` apt install -y ffmpeg libsm6 libxext6 pip install opencv-python ``` --- 1. Update the repository: ```shell= sudo apt-get update ``` --- 2. Download the required packages to compile OpenCV: ```shell= sudo apt-get install build-essential cmake git libgtk2.0-dev pkg-config libavcodec-dev libavformat-dev libswscale-dev ``` --- 3. Install the developer packages for Python3.5: ```shell= sudo apt-get install python3.5-dev ``` --- 4. Copy the dev files: **python3.5-config --includes** The output should be similar to: **-I/usr/include/python3.5m** **-I/usr/include/x86_64-linux-gnu/python3.5m**. The first part of the output is the expected location & the second part shows the current location of the config file. To solve this problem, we’ll copy the file from the current location to the expected location: ```shell= sudo cp /usr/include/x86_64-linux-gnu/python3.5m/pyconfig.h /usr/include/python3.5m/ ``` --- 5. Create a temporary directory, move into it and run: ```shell= git clone https://github.com/opencv/opencv.git ``` This will download OpenCV 3. Then rename the folder **opencv** to **opencv-3** --- 6. Create a **build** directory, move to it and run: ```shell= cmake -D CMAKE_BUILD_TYPE=RELEASE -D CMAKE_INSTALL_PREFIX=/usr/local ../opencv-3 ``` After the process is finished, run ``` make ``` and then ```sudo make install```. Enjoy.
Last changed by  
 
謝朋諺
目前是 MobileDrive 富智捷公司的 Sr. Machine Learning Engineer，主要專長與工作內容在 深度學習、機器學習、影像處理、模型部屬等等，前後待過 QNAP、Appier 公司，現在專職在做 ADAS 相關的研究與實作。
135

Read more

3D Object Detection - Multi-task Learning

[name=謝朋諺(Adam Hsieh)] [time=Mon, Oct 2, 2023 10:37 AM] Reference 26. Which Tasks Should Be Learned Together in Multi-task Learning? - 多任务网络训练关系研究 CSDN - Which Tasks Should Be Learned Together in Multi-task Learning? 論文連結 Outline

4/18/2024
Object Detection - PAA

[name=謝朋諺(Adam Hsieh)] [time=Thu, Nov 19, 2020 3:09 PM] Reference Probabilistic Anchor Assignment with IoU Prediction for Object Detection论文阅读翻译 - 2020ECCV （三十七）论文阅读 | 目标检测之PAA 目标检测 PAA 概率anchor分配算法（Probabilistic Anchor Assignment Algorithm） 目标检测 PAA - 高斯混合模型（GMM）和期望最大化算法（EM algorithm） ECCV 2020 | 53.5 AP！PAA：用于目标检测的IoU预测的概率Anchor分配

7/21/2023
Object Detection - YOLO v4

[name=謝朋諺(Adam Hsieh)] [time=Thu, Jul 16, 2020 2:47 PM] Reference YOLOv4全文閱讀（全文中文翻譯） 深入浅出Yolo系列之Yolov3&Yolov4核心基础知识完整讲解 炸了！吊打一切的 YOLOv4 重磅来袭！ [一张图梳理YOLOv4论文](https://www.cnblogs.com/ppr０ p/p/12771430.html) YOLO v4它来了：接棒者出现，速度效果双提升

11/2/2021
Person Re-Identification - MGN

[name=謝朋諺(Adam Hsieh)] [time=Mon, Jun 3, 2019 4:10 PM] Reference 論文筆記（2）--（Re-ID） Learning Discriminative Features with Multiple Granularities for Person Re-Id 多粒度网络（MGN）的结构设计与技术实现 刷新三数据集纪录的跨镜追踪(行人再识别-ReID)技术介绍 Learning Discriminative Features with Multiple Granularities for Person Re-Identification 論文翻譯&筆記 《Learning Discriminative Features with Multiple Granularities for Person Re-Identification》论文阅读之MGN

10/6/2021
Read more from 謝朋諺
Published on HackMD