Portfolio Details


Cats vs Dogs CNN Classification

Image classification project using Convolutional Neural Networks (CNN)

This project aims to classify cat and dog images using a Convolutional Neural Network (CNN). The goal is to build a fundamental deep learning model with data augmentation techniques and visualize the training and validation performance.

Project Overview

The dataset was obtained from Kaggle and consists of over 35,000 labeled images. Images were resized to 150x150 pixels and normalized before training. Data augmentation techniques such as rotation, zoom, and horizontal flipping were applied to improve model generalization.

A Sequential CNN model was built using Conv2D, MaxPooling, Dense, and Dropout layers. The model was trained for 15 epochs using the Adam optimizer and Binary Crossentropy loss function.

Project Information

  • Category: AI - Deep Learning
  • Developer: Yasin Kucuker
  • Project Date: 2025
  • Theme: CNN Image Classification

Features

  • Image Preprocessing: Image resizing and normalization (150x150, rescale=1./255).
  • Data Augmentation: Rotation, zoom, width/height shift, and horizontal flip.
  • CNN Architecture: 3 Conv2D + MaxPooling layers with Dense and Dropout.
  • Binary Classification: Sigmoid activation for cat vs dog prediction.
  • Model Evaluation: Confusion Matrix, Classification Report, Accuracy.