Skip to content

Latest commit

 

History

History
49 lines (31 loc) · 1.14 KB

README.md

File metadata and controls

49 lines (31 loc) · 1.14 KB

CIFAR-10 Image Classification App

This project uses a deep learning model built with TensorFlow/Keras to classify images from the CIFAR-10 dataset. It includes a user-friendly Streamlit interface where users can upload an image and see classification results with prediction probabilities.

Project Features

  • CNN Model Training on the CIFAR-10 dataset
  • Data Augmentation using ImageDataGenerator
  • Callbacks for early stopping and learning rate reduction
  • Model Saving in .h5 format
  • Streamlit Interface for real-time image classification
  • Visualization of training accuracy and confusion matrix

Technologies Used

  • TensorFlow / Keras
  • NumPy, Matplotlib, Seaborn
  • Streamlit
  • scikit-learn

  • Example Output

  • Predictions:

  1. frog (92.4%)
  2. cat (3.1%)
  3. deer (2.0%) -- Project Structure

Cifar-10-Classification/

├── app.py # Streamlit interface

├── model.ipynb # Model training script

├── cifar10_gelismis_model.h5 # Trained model

├── README.md # Project documentation Developer Seda Ozkaya GitHub: sedaozkaya