Machine Learning Projects

This repository showcases a collection of end-to-end machine learning projects demonstrating practical experience across model development, training, evaluation, and deployment.

The work emphasizes reproducibility, clean experimentation, and best practices, with reusable templates and utility scripts that support real-world machine learning workflows.

The projects span multiple domains, including:

• Computer Vision — image classification pipelines (e.g., food image classification, Vision Transformers)
• Natural Language Processing (NLP) — binary text classification and dataset creation
• Retrieval-Augmented Generation (RAG) — building local RAG systems from scratch

Technical Focus

• Transfer learning and model fine-tuning
• Custom dataset creation and preprocessing
• Training and evaluation workflows in PyTorch
• Experimentation with modern architectures (ViT, EffNetB2)
• Model deployment and inference pipelines using Gradio
• Hugging Face–based NLP and multimodal workflows

Repository Structure

├── PyTorch_Deep_Learning/
│   ├── 01_PyTorch_tutorial.ipynb
│   ├── 02_Classification_Using_PyTorch.ipynb
│   ├── 03_PyTorch_Computer_Vision.ipynb
│   ├── 04_PyTorch_Computer_Vision_Customized_Dataset.ipynb
│   ├── 06_PyTorch_transfer_learning.ipynb
│   ├── 08_ViT_for_foodvision_using_PyTorch.ipynb
│   ├── 09_model_deployment.ipynb
│   └── README.md
├── RAG_project/
│   ├── Local_RAG_from_Scratch.ipynb
│   └── README.md
├── huggingface_project/
│   ├── huggingface_text_classification.ipynb
│   ├── huggingface_food_not_food_image_caption_dataset_creation.ipynb
│   └── README.md
├── README.md
├── .gitignore
└── LICENSE