https://github.com/oemanuelfirmino/image_classifier

A deep learning model using CNN to classify dog and cat images, with an interactive Streamlit interface for real-time predictions and training visualizations.
https://github.com/oemanuelfirmino/image_classifier

data-science deep-learning machine-learning neural-network python

Last synced: about 1 month ago
JSON representation

A deep learning model using CNN to classify dog and cat images, with an interactive Streamlit interface for real-time predictions and training visualizations.

• Host: GitHub
• URL: https://github.com/oemanuelfirmino/image_classifier
• Owner: oEmanuelFirmino
• License: mit
• Created: 2025-01-09T02:27:32.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2026-02-07T01:41:24.000Z (5 months ago)
• Last Synced: 2026-02-07T13:07:25.543Z (5 months ago)
• Topics: data-science, deep-learning, machine-learning, neural-network, python
• Language: Python
• Homepage:
• Size: 1.17 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          

# Image Classifier

A deep learning model using Convolutional Neural Networks (CNN) to classify images of dogs and cats. The project features an interactive Streamlit interface for real-time image prediction and visualization of model training metrics.

## Features

- Upload images of dogs or cats for classification.

- Real-time predictions with confidence scores.

- Visualization of training history (accuracy, loss).

- Displays model architecture summary.

## Technologies Used

- **TensorFlow/Keras**: For the deep learning model.

- **Streamlit**: For building the web interface.

- **Plotly**: For interactive data visualizations.

- **Matplotlib**: For training history plots.

## Installation

1. Clone this repository:

   ```bash

   git clone https://github.com/oEmanuelFirmino/image_classifier.git

   ```

2. Install the required dependencies:

   ```bash

   pip install -r requirements.txt

   ```

3. Run the Streamlit app:

   ```bash

   streamlit run app.py

   ```

## Model Training

The model is a Convolutional Neural Network (CNN) with the following architecture:

- 3 Convolutional layers with MaxPooling.

- Global Average Pooling layer.

- Fully connected Dense layer with 128 neurons.

- Dropout regularization to prevent overfitting.

## License

This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.