Detecting and locating objects is one of the most common uses of deep learning for computer vision. Applications include helping autonomous systems navigate complex environments, locating medical conditions like tumors, and identifying ready-to-harvest crops in agriculture. In the course projects, you will apply detection models to real-world scenarios and train a model to detect various parking signs. Completing this course will give you the skills to train detection models for your application.
By the end of this course, you will be able to:
• Explain how deep learning networks locate and classify objects in images
• Retrain popular YOLO deep learning models for your application
• Use a variety of metrics to evaluate prediction results
• Visualize results to gain insights into model performance
• Improve model performance by adjusting important model parameters
• Analyze labeled images to identify and fix potential shortcomings in your data
For the duration of the course, you will have free access to MATLAB, software used by top employers worldwide. The courses draw on the applications using MATLAB, so you spend less time coding and more time applying deep learning concepts.
Overview
Syllabus
- Detecting Objects with Pre-trained Models
- Get started with object detection by using pre-trained models
- Training Object Detection Models
- Use transfer learning to retrain YOLO models for new applications
- Evaluating Object Detection Models
- Use metrics like recall, precision, and mean average precision to evaluate your models
- Final Project: Train and Evaluate a Detection Model
- Apply the full object detection workflow on a final project
Taught by
Amanda Wang, Matt Rich, Megan Thompson, Mehdi Alemi and Brandon Armstrong
