Welcome to my Queen Mary University of London (QMUL) repository! 🎓 This repository contains multiple projects focusing on Computer Vision, Deep Learning, and AI-based applications. Each project explores different aspects of machine learning, image processing, and explainable AI techniques.
- Fundamental concepts of Computer Vision.
- Includes texture classification, image processing, and feature extraction techniques.
- Useful for beginners to understand image representation and preprocessing.
- Uses GANs (Generative Adversarial Networks) to generate handwritten digits similar to the MNIST dataset.
- Implemented with PyTorch, focusing on generator-discriminator adversarial training.
- Experimented with different learning rates, batch sizes, and dropout strategies.
- Implements a Super-Resolution Convolutional Neural Network (SRCNN) for image enhancement.
- Uses deep learning to upscale low-resolution images while preserving details.
- Benchmark results on standard datasets.
git clone https://github.com/Abhi5ingh/QMUL.git
cd QMULEach project is structured independently. To run a specific project:
cd <project-folder>
pip install -r requirements.txt
python main.pyDeep Learning Applications: Hands-on projects implementing state-of-the-art neural networks.
Explainable AI (XAI): Focus on interpretability techniques like Grad-CAM, SHAP, LIME.
Computer Vision Techniques: Super-resolution, GANs, and classification models.
Optimized PyTorch Implementations: Efficient training and inference pipelines.
Scalable & Modular Code: Organized project structure with well-documented code.
Interested in collaborating or improving these projects? Feel free to:
- ⭐ Star this repository to support!
- 🛠️ Fork & contribute with pull requests.
- 🔗 Reach out for discussions!
Email: [email protected]
GitHub: Abhi5ingh
LinkedIn: Abhishek