This repository contains code and resources for a Convolutional Neural Network (CNN) project on the CIFAR-10 dataset. The CIFAR-10 dataset consists of 60,000 32x32 color images in 10 different classes, with 6,000 images per class. The goal of this project is to train a CNN to accurately classify these images into their respective classes.
-
data: Contains the CIFAR-10 dataset. You can download it from CIFAR-10 and place it in this directory.
-
models: Stores trained CNN models.
-
notebooks: Jupyter notebooks for exploratory data analysis, model training, and evaluation.
Accuracy : 74%