Course Outline
Introduction
Overview of Features and Architecture of YOLO Pre-trained Models
- The YOLO Algorithm
- Regression-Based Algorithms for Object Detection
- How YOLO Differs 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
- Darknet Implementation
- PyTorch and Keras Implementations
- Running OpenCV and NumPy
Overview of Object Detection Using YOLO Pre-trained Models
Building and Customizing Python Command-Line Applications
- Labeling Images with the YOLO Framework
- Image Classification Based on a Dataset
Detecting Objects in Images with YOLO Implementations
- Understanding How Bounding Boxes Work
- Evaluating YOLO's Accuracy 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
- Differences from Basic Image Processing
Training and Testing YOLO Implementations Within the Framework
Troubleshooting and Debugging
Summary and Conclusion
Requirements
- Programming experience with Python 3.x
- Basic familiarity with any Python IDEs
- Experience using Python argparse and command-line arguments
- Understanding of computer vision and machine learning libraries
- Knowledge of 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.
