Project: Perform Real-Time Object Detection with YOLOv3


Perform real-time object detection with YOLOv3

Use pre-trained models to perform real-time and passive inference with a GPU

Use OpenCV to manipulate video data and develop a command line application with Python for inference

Clock1.5 hours
Comment Dots英语(English) + subtitles

In this 1-hour long project-based course, you will perform real-time object detection with YOLOv3: a state-of-the-art, real-time object detection system. Specifically, you will detect objects with the YOLO system using pre-trained models on a GPU-enabled workstation. To apply YOLO to videos and save the corresponding labelled videos, you will build a custom command-line application in Python that employs a pre-trained model to detect, localize, and classify objects. It will use OpenCV to read the video streams, draw bounding boxes around detected objects, label the objects along with confidence scores, and save the labelled videos to disk. This course runs on Coursera's hands-on project platform called Rhyme. On Rhyme, you do projects in a hands-on manner in your browser. You will get instant access to pre-configured cloud desktops containing all of the software and data you need for the project. Everything is already set up directly in your internet browser so you can just focus on learning. For this project, you’ll get instant access to a cloud desktop with Python, Jupyter, and Keras pre-installed. Notes: - You will be able to access the cloud desktop 5 times. However, you will be able to access instructions videos as many times as you want. - This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions.


Deep LearningOpencvYOLOObject DetectionComputer Vision



  1. Introduction and Overview

  2. Explore the Dataset

  3. Setup Training and Validation Data Generators

  4. Create a Convolutional Neural Network (CNN) Model

  5. Train and Evaluate Model

  6. Save and Serialize Model as JSON String

  7. Create a Flask App to Serve Predictions

  8. Create a Model Class to Output Predictions

  9. Design an HTML Template for the Flask App

  10. Use Model to Recognize Facial Expressions in Videos






  • 购买项目后,您将获得完成项目所需的一切内容,包括通过 Web 浏览器访问云桌面工作空间,其中包含您需要了解的文件和软件,以及特定领域的专家提供的分步视频说明。

  • 因为您的工作空间包含适合笔记本电脑或台式计算机使用的云桌面,所以项目不在移动设备上使用。

  • 项目讲师是特定领域的专家,他们在项目的技能、工具或领域上都很有经验,并且热衷于分享自己的知识以影响全球数百万的学生。

  • 您可以从项目中下载并保留您创建的任何文件。为此,您可以在访问云桌面时使用‘文件浏览器’功能。

  • 项目没有助学金。

  • 您不需要任何前期经验即可开始项目。讲师将逐步指导您完成项目。

  • 是,您可以在浏览器的云桌面中获得完成项目所需的一切。

  • 您可以通过直接在浏览器中的分屏环境中完成项目来进行学习。在屏幕的左侧,您将在工作空间中完成任务。在屏幕的右侧,您将看到有讲师逐步指导您完成项目。