🚧 [Work in Progress] - I am currently updating this repository weekly as I progress through the bootcamp.
Welcome to my repository for the Generative AI & Computer Vision Bootcamp at Hamrah Academy. This intensive 12-week program focuses on modern AI technologies, specifically in the visual domain, covering everything from core mathematics to advanced Generative AI and Multimodal models.
This repository contains all my codes, projects, and assignments from the bootcamp. It serves as a comprehensive showcase of my journey in mastering Computer Vision and Generative AI.
The program consists of over 200 hours of specialized training. Here is the breakdown of my learning path:
- 🐍 Python Programming (19 Hours) From pixel processing to deep visual intelligence.
- 🎯 Supervised Machine Learning (21 Hours) Intelligent decision-making from labeled data.
- 🔍 Unsupervised Machine Learning (19 Hours) Uncovering hidden patterns in images using unlabeled data.
- 📐 Mathematics in Data Science & AI (14 Hours) The mathematical foundations of AI for image processing.
- 🧠 Deep Learning (19 Hours) Neural network architectures for advanced image analysis.
- 🎞️ Image & Video Processing (23 Hours) Advanced techniques in digital image engineering.
- 👁️🗨️ Computer Vision (33 Hours) Modern algorithms for object detection and scene analysis.
- 🎨 Generative AI in Computer Vision (23 Hours) Utilizing generative models (GANs, Diffusion, etc.) for visual content creation.
- 🔗 Multimodal AI (14 Hours) Practical applications of multimodal models in machine vision.
- 💬 Prompt Engineering (16 Hours) Designing Vision-Language models through professional prompting.
00_workshop/01_python_programming/02_supervised_machine_learning/03_mathematics_in_data_science_and_ai/04_unsupervised_machine_learning/
Python | OpenCV | PyTorch / TensorFlow | Scikit-Learn | CNNs | GANs | Diffusion Models | Vision-Language Models
Author: Erfan Masoudi Contact/LinkedIn: [Erfan Masoudi]