Object Detection Using Facebook's Detectron2

Offered By
Coursera Project Network
In this Guided Project, you will:

Create an Object Detection Model using Facebook's Detectron2.

Make Inferences Using the Object Detection Model

Clock2 hours
IntermediateIntermediate
CloudNo download needed
VideoSplit-screen video
Comment DotsEnglish
LaptopDesktop only

In this 2-hour long project-based course, you will learn how to train an Object Detection Model using Facebook's Detectron2. Detectron2 is a research platform and a production library for deep learning, built by Facebook AI Research (FAIR). We will be building an Object Detection Language Identification Model to identify English and Hindi texts written which can be extended to different use cases. We will look at the entire cycle of Model Development and Evaluation in Detectron2. We will first look at how to load a dataset, visualize it and prepare it as an input to the Deep Learning Model. We will then look at how we can build a Faster R-CNN model in Detectron2 and customize it. We will then configure the parameters & hyperparameters of the model. We will then move on to training the Model and subsequently to model inference and evaluation. Note: 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.

Skills you will develop

Computer VisionObject DetectionDeep LearningDetectron2

Learn step-by-step

In a video that plays in a split-screen with your work area, your instructor will walk you through these steps:

  1. Introduction to Detectron2 & Setup

  2. Preparing and loading the Dataset

  3. Visualizing the Dataset

  4. Build and Customizing the Training Model

  5. Configuring & Training the Model

  6. Inference & Evaluation

How Guided Projects work

Your workspace is a cloud desktop right in your browser, no download required

In a split-screen video, your instructor guides you step-by-step

Frequently asked questions

Frequently Asked Questions

More questions? Visit the Learner Help Center.