This repository contains lab practicals from the Deep Learning course at ADYPU-SOE. The projects cover key topics in deep learning, including logistic regression, cost and loss functions, development of Convolutional Neural Networks (CNNs), and more.
All datasets are stored in a single folder for simplicity and easy access:
-
Datasets Folder:
Contains all the datasets required for the practicals, including datasets for Logistic Regression, Cost & Loss Functions, Gradient Descent & Regularization, and Potato Disease Prediction. -
HR Folder:
Implements Logistic Regression to classify human resources data. It covers the basics of logistic regression and its applications in binary classification. -
Insurance Folder:
Focuses on Cost & Loss Functions, Gradient Descent, and Regularization. It demonstrates how to optimize a machine learning model using these techniques to improve accuracy and avoid overfitting. -
Potato Disease Folder:
Implements a Convolutional Neural Network (CNN) to predict potato disease from images. This project explores image classification with deep learning techniques and demonstrates how CNNs can be used for real-world applications like agriculture.
All required datasets can be found in the Datasets folder. You will find datasets related to the following:
- HR dataset for Logistic Regression
- Insurance dataset for Cost & Loss Functions and Gradient Descent
- Potato Disease dataset for CNN-based prediction
Feel free to fork the repository and make improvements. If you have any suggestions or bug fixes, feel free to create a pull request.
This repository is licensed under the MIT License - see the LICENSE file for details.
To run the lab practicals, ensure you have the required dependencies. You can install them using the following:
pip install -r requirements.txt