/CIFAR10-Dataset

CIFAR-10 Image Classification project focuses on using Convolutional Neural Networks (CNN) to classify 32x32 color images into ten distinct classes. The goal is to design and train an effective CNN model using the CIFAR-10 dataset, enabling accurate image classification across various categories.

Primary LanguageJupyter NotebookMIT LicenseMIT

CIFAR-10 Image Classification using Convolutional Neural Networks (CNN)

Overview

This repository is dedicated to the application of Convolutional Neural Networks (CNN) for image classification on the CIFAR-10 dataset. The main objective is to leverage machine learning techniques to analyze and predict the classes of images within the CIFAR-10 dataset.

Dataset

The dataset employed in this project is the CIFAR-10 dataset, which consists of 60,000 32x32 colour images across 10 distinct classes. Each class contains 6,000 images, with a division of 50,000 for training and 10,000 for testing.

Classes:

  1. Airplane
  2. Automobile
  3. Bird
  4. Cat
  5. Deer
  6. Dog
  7. Frog
  8. Horse
  9. Ship
  10. Truck

Convolutional Neural Networks (CNN)

Convolutional Neural Networks (CNNs) play a crucial role in this project, as they are well-suited for image classification tasks. CNNs excel at capturing spatial hierarchies and learning intricate patterns from image data.

Documentation

The documentation for this assignment can be found here

Google Colab

This assignment was completed in Google Colab, an online platform for Python programming and Machine Learning.

License

This project is licensed under the MIT License.