Course Outline
Introduction
Overview of YOLO Pre-trained Models Features and Architecture
- The YOLO Algorithm
- Regression-based Algorithms for Object Detection
- How is YOLO Different from RCNN?
Selecting the Appropriate YOLO Variant
- Features and Architecture of YOLOv1-v2
- Features and Architecture of YOLOv3-v4
Installing and Configuring the IDE for YOLO Implementations
- The Darknet Implementation
- The PyTorch and Keras Implementations
- Executing OpenCV and NumPy
Overview of Object Detection Using YOLO Pre-trained Models
Building and Customizing Python Command-Line Applications
- Labeling Images Using the YOLO Framework
- Image Classification Based on a Dataset
Detecting Objects in Images with YOLO Implementations
- How do Bounding Boxes Work?
- How Accurate is YOLO for Instance Segmentation?
- Parsing Command-line Arguments
Extracting YOLO Class Labels, Coordinates, and Dimensions
Displaying the Resulting Images
Detecting Objects in Video Streams with YOLO Implementations
- How is it Different from Basic Image Processing?
Training and Testing YOLO Implementations on a Framework
Troubleshooting and Debugging
Summary and Conclusion
Requirements
- Programming experience with Python 3.x
- Basic knowledge of any Python IDEs
- Experience with Python argparse and command-line arguments
- Understanding of computer vision and machine learning libraries
- Familiarity with fundamental object detection algorithms
Audience
- Backend Developers
- Data Scientists
Testimonials (2)
Hands on and the practical
Keeren Bala Krishnan - PENGUIN SOLUTIONS (SMART MODULAR)
Course - Computer Vision with Python
I genuinely enjoyed the hands-on approach.
