Image Classification with CNN

This project demonstrates how I built and trained a Convolutional Neural Network (CNN) for image classification using Keras and TensorFlow. The model is trained to classify images of cats and dogs in contexte of a Kaggle competition by School of AI club.

Project Structure

• submission.ipynb: Jupyter Notebook containing the code for splitting the dataset, data augmentation, and training the model.
• upgrade.ipynb: Jupyter Notebook containing the upgraded code that is in submission.ipynb, but I run it after the competition because of its long time training.
• submission.csv: CSV file containing the predictions for the test images.
• test_petimages/: Directory containing the test images. (Provided by SOAI)
• train_petimages/: Directory containing the train images. (Provided by SOAI)

Requirements

• Python 3.x
• TensorFlow
• Keras
• pandas
• numpy
• matplotlib
• Pillow

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/your-repo-name.git
   cd your-repo-name
   

Competition link