Course Outline
Introduction
Overview of YOLO Pre-trained Models: Features and Architecture
- 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 Implementation
- The Darknet Implementation
- Implementations using PyTorch and Keras
- Utilizing 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
Object Detection in Images with YOLO Implementations
- Understanding Bounding Boxes
- Accuracy of YOLO for Instance Segmentation
- Parsing Command-line Arguments
Extracting YOLO Class Labels, Coordinates, and Dimensions
Displaying Resulting Images
Object Detection in Video Streams with YOLO Implementations
- Differences from Basic Image Processing
Training and Testing YOLO Implementations on a Framework
Troubleshooting and Debugging
Summary and Conclusion
Requirements
- Experience with Python 3.x programming.
- Basic familiarity with Python IDEs.
- Experience using 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.
