🧠 Deep Learning Image Classifier with CNN

A project exercise ordered by IronHack to build a Convolutional Neural Network (CNN) model that classifies images from the CIFAR-10 dataset into predefined categories.

---

🚀 Project Overview

This project demonstrates the use of a deep learning approach to image classification using Convolutional Neural Networks (CNNs).
The goal is to train and evaluate a model capable of recognizing and categorizing images from the CIFAR-10 dataset into 10 different classes, such as airplanes, cars, birds, cats, etc.

---

🧰 Requirements

This notebook is designed to run on Google Colab.

Make sure you have:

• A Google account
• Internet access

All necessary libraries are pre-installed in Colab, including:

• tensorflow
• keras
• numpy
• matplotlib

---

📂 Project Structure

Deep_Learning_Img_Classification_with_CNN/ │ ├── APP.py # Optional Python script (for local app or testing) ├── Architecture Notes.xlsx # Architecture notes and project planning ├── Group 2.pdf # Group presentation as PDF file ├── Group 2.pptx # Group presentation slides ├── imgPixel32x32.7z # Compressed image dataset (optional/local data) ├── Project_I___Deep_Learning_Image_Classification_with_CNN.ipynb # Main Jupyter Notebook └── README.md # Project documentation

---

▶️ How to Run the Project in Google Colab

1. Click the "Open in Colab" badge at the top of this README.
   (Or open the notebook manually in Colab: File → Open Notebook → GitHub → paste your repo URL)

2. Run all cells sequentially:
   Runtime → Run all

3. Review the model summary, training results, and evaluation metrics at the end of the notebook.

---

🧪 Dataset Details

CIFAR-10 Dataset

• 60,000 color images (32x32 pixels)
• 10 classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck
• 50,000 training images and 10,000 test images

The dataset is automatically downloaded via Keras’ built-in datasets API.

---

📊 Results & Evaluation

The CNN model is evaluated using:

• Accuracy and loss metrics
• Confusion matrix and classification report (optional)
• Visualization of training and validation performance over epochs

---

👩‍💻 Authors

Developed collaboratively by:

• Inna Ivanova
• Mauricio Dahbar
• Sandra Vuong
• Tiago Borges

For: IronHack Artificial Intelligence FT October Boothcamp 2025

---

📄 License

This project is shared for educational purposes.
Feel free to reference or build upon it with proper credit to the authors.

---

🌐 Acknowledgments

• IronHack for providing the project framework.
• CIFAR-10 Dataset for the data used.
• TensorFlow and Keras for the deep learning framework.