https://github.com/sunnybibyan/image-classification

This project implements a Convolutional Neural Network (CNN) to classify images from the CIFAR-10 dataset, which consists of 60,000 32x32 color images across 10 classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck.
https://github.com/sunnybibyan/image-classification

batchnormalization cnn-keras early-stopping-with-patience image-classification

Last synced: 12 months ago
JSON representation

This project implements a Convolutional Neural Network (CNN) to classify images from the CIFAR-10 dataset, which consists of 60,000 32x32 color images across 10 classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, and truck.

• Host: GitHub
• URL: https://github.com/sunnybibyan/image-classification
• Owner: SunnyBibyan
• License: mit
• Created: 2024-10-09T10:14:55.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-10-21T07:08:38.000Z (over 1 year ago)
• Last Synced: 2025-01-05T08:55:11.375Z (about 1 year ago)
• Topics: batchnormalization, cnn-keras, early-stopping-with-patience, image-classification
• Language: Jupyter Notebook
• Homepage:
• Size: 113 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# CIFAR-10 CNN Classifier

This project demonstrates a CNN-based approach to classify images from the CIFAR-10 dataset using TensorFlow and Keras.

## How to Run

1. Install dependencies:

   ```bash

   pip install -r requirements.txt

## Summary

The trained model reached a test accuracy of over 89% with a relatively simple model-structure and only minor overfitting due to different regularization techniques like Dropout, and EarlyStopping. But there is still a lot of optimization potential.