https://github.com/mehrab-kalantari/cnn-cifar-10

Building a Convolutional Neural Network on CIFAR-10 dataset
https://github.com/mehrab-kalantari/cnn-cifar-10

cifar-10 cnn convolutional-neural-networks data-augmentation deep-learning

Last synced: 4 months ago
JSON representation

Building a Convolutional Neural Network on CIFAR-10 dataset

• Host: GitHub
• URL: https://github.com/mehrab-kalantari/cnn-cifar-10
• Owner: Mehrab-Kalantari
• Created: 2023-09-07T17:55:31.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2023-09-07T18:11:01.000Z (about 2 years ago)
• Last Synced: 2025-06-04T22:11:42.725Z (5 months ago)
• Topics: cifar-10, cnn, convolutional-neural-networks, data-augmentation, deep-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 576 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# CIFAR-10 Dataset Image Classification using CNN

[Dataset on kaggle](https://www.kaggle.com/datasets/fedesoriano/cifar10-python-in-csv)

## Contents

### Data Preprocessing

* Scaling

* Encoding

### Modeling

We use the following architecture for our model

![m](sample/model.png)

### Model Improving

Here we use some techniques to avoid overfitting and increase the accuracy

* Early stopping

* Data augmentation

### Evaluation

We use precision, recall and accuracy as metrics in our model

* Classification report

* Confusion matrix

* Plotting

* ![p](sample/output.png)