Course Outline
Introduction
Overview of Features and Architecture in YOLO Pre-trained Models
- The YOLO Algorithm
- Regression-Based Algorithms for Object Detection
- Differences Between YOLO and 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
- Implementations Using PyTorch and Keras
- Executing 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 via YOLO Implementations
- How Bounding Boxes Function
- YOLO Accuracy for Instance Segmentation
- Parsing Command-line Arguments
Extracting YOLO Class Labels, Coordinates, and Dimensions
Displaying Resulting Images
Detecting Objects in Video Streams with YOLO Implementations
- How This Differs 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
- Familiarity with Python IDEs
- Experience using Python argparse and command-line arguments
- Understanding of computer vision and machine learning libraries
- Knowledge of fundamental object detection algorithms
Target 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.
