This course navigates students through the exciting realm of AI, spotlighting Computer Vision applications. Starting from Python programming and Git, it smoothly transitions into developing AI applications using Docker and OpenCV. Assignments each week provide hands-on experience, cementing the key learnings.
- Python Programming: Understand syntax, variables, loops, conditionals, lists, tuples, and dictionaries
- Starting with Git: Learn to clone, commit, branch, and merge
Cement your knowledge of Python and Git basics through programming exercises. They allow you to practically apply loops, conditionals, and data structures using Python while managing your code with Git.
- Upgraded Python: Study functions, classes, exception handling, file I/O
- Python libraries: Get to know Numpy and Pandas
- Numpy: Learn about arrays, indexing, datatypes, math functions, and broadcasting
Engage in multi-faceted exercises around Numpy and Pandas to manipulate data. This will also entail committing changes to your Git repository, translating the theory into action.
- Jupyter Notebooks: Understand installation, creating notebooks, markdown, export, and share features
Execute Python programs in Jupyter Notebooks, thereby exploring the adaptability and utility of this tool for coding.
- AI and Computer Vision: Delve into their history and applications
- Machine Learning: Learn about supervised vs unsupervised learning, and an array of algorithms
Review literature around AI, Computer Vision, and Machine Learning to grasp their practical applications.
- Scikit-Learn: Understand Regression, Classification, Clustering, Model Validation
Leverage Scikit-Learn to build basic models, transforming abstract concepts into real, tangible software constructs.
- Docker: Grasp containers, Dockerfile, Docker images, Docker Compose
- Docker Development Environment: Get it set up
Harness Docker to create a simple application. This way, you directly experience creating, deploying, and managing applications.
- Computer Vision: Strengthen foundational knowledge
- OpenCV: Learn to read images and videos, implement basic image operations, work on image processing and feature detection
Utilize OpenCV for basic image processing tasks, advancing your understanding of the application of Computer Vision.
- Advanced Computer Vision: Discover object detection, tracking, segmentation, and recognition
- Deep Learning in Computer Vision: An introduction
- Project: Create an AI application utilizing Python, Git, Docker, Machine Learning, and Computer Vision
Implement object detection using OpenCV to exercise advanced computer vision concepts. Additionally, work on your project, a significant opportunity to fuse all you've learned throughout the course.
- Review: Take a look back at all the topics.
- Project Presentation: Share your hard work with your peers.
- Course Conclusion: Wrap up the course and look towards future learning opportunities in AI and Computer Vision
By the close of this course, students should be proficient in Python, Numpy, Pandas, Scikit-learn, Git, Jupyter Notebooks, Docker, and OpenCV. Through assignments and a capstone project, they will gain practical experience and knowledge on building AI applications for computer vision tasks.