Skip to content

The Deep-Learning repo contains four Jupyter notebooks: Untitled0.ipynb – Basics of neural networks Untitled1.ipynb– Training and backpropagation Untitled2.ipynb – Likely covers CNNs for image tasks Untitled3.ipynb – Likely explores RNNs or sequential data Together, they offer hands-on practice with core deep learning

Notifications You must be signed in to change notification settings

Reet-Kamlay/Deep-Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🧠 Deep Learning Projects

This repository contains a collection of deep learning projects built using Python, TensorFlow, Keras, and PyTorch. These projects demonstrate the implementation of fundamental and advanced concepts such as image classification, object detection, convolutional neural networks (CNNs), and more.

Each project is structured for clarity and includes a Jupyter Notebook (.ipynb) with code, visualizations, and explanations.

📁 Contents

The Google Drive link below contains all associated notebooks, trained models, and datasets (if too large for GitHub).

🔗 Drive Folder: Deep Learning Notebooks & Files

📌 Projects Included

  • Image Classification using CNN
    • MNIST / CIFAR-10 datasets
    • Built with Keras and TensorFlow
  • Custom Dataset Classification
    • Transfer Learning (e.g. using MobileNet or ResNet)
  • Face Mask Detection
    • Trained model to detect face masks in real-time
  • Food Image Classifier
    • Multi-class image classification of food items
  • Binary Classification Tasks
    • E.g., Tumor detection, cat vs dog, etc.

🛠️ Tech Stack

  • Python 3.x
  • Jupyter Notebook
  • TensorFlow / Keras
  • PyTorch (in some notebooks)
  • OpenCV (for preprocessing and real-time demos)
  • Matplotlib, NumPy, Pandas for data manipulation and visualization

🚀 Getting Started

1. Clone the Repository

git clone https://github.com/Reet-Kamlay/Deep-Learning.git
cd Deep-Learning

2. Setup Environment

It's recommended to use a virtual environment:

python -m venv venv
source venv/bin/activate  # On Windows use: venv\Scripts\activate
pip install -r requirements.txt  # If provided

Or manually install:

pip install numpy pandas matplotlib opencv-python tensorflow keras

3. Open a Notebook

jupyter notebook

Then open any .ipynb file and run the cells.

📦 Additional Resources

  • Model files, datasets, and extra notebooks are available in the Google Drive folder.
  • Some notebooks may require you to download additional data (check notebook instructions or Drive).

👨‍💻 Author

Reet Kamlay
GitHub: @Reet-Kamlay


This repo is intended for educational and experimental use. Contributions and suggestions are welcome!

About

The Deep-Learning repo contains four Jupyter notebooks: Untitled0.ipynb – Basics of neural networks Untitled1.ipynb– Training and backpropagation Untitled2.ipynb – Likely covers CNNs for image tasks Untitled3.ipynb – Likely explores RNNs or sequential data Together, they offer hands-on practice with core deep learning

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published