Skip to content

Image classifier desktop app using TensorFlow and Tkinter. Upload an image and get predictions with confidence scores.

Notifications You must be signed in to change notification settings

nievyx/ImageClassifierGUI

Repository files navigation

🖼️ ImageClassifierGUI

A simple desktop application that classifies images using a pre-trained neural network. Built with Python, TensorFlow, and a Tkinter GUI. Just upload an image of an object (like a dog, cat, boat, car, etc.) and the app will guess what it is — with a confidence score.

App Demo


✨ Features

  • Upload any image from your device
  • Predicts object category using a trained neural network
  • Displays confidence level for each prediction
  • Easy-to-use graphical interface (Tkinter)

📂 Project Structure

ImageClassifierGUI/

├── classifier.py # Main application file (GUI + logic)
├── model.keras # Pre-trained model file
├── logo.png # App logo
├── assets/
│ └── demo.gif # Screenshot or demo gif for README
├── requirements.txt # Dependencies
└── README.md # Project overview (this file)

🚀 Installation

  1. Clone the repository:
    git clone https://github.com/yourusername/ImageClassifierGUI.git
    cd ImageClassifierGUI
  2. Create a virtual environment (optional but recommended):
    python -m venv venv
    # On macOS/Linux:
    source venv/bin/activate
    # On Windows:
    venv\Scripts\activate
  3. Install dependencies:
    pip install -r requirements.txt

🧪 Usage

Run the app:

python classifier.py

Upload an image and see what it predicts!

🧠 Model Info

This project uses a pre-trained Keras image classification model trained on a simplified dataset of common object categories.

📸 Demo

Demo GIF

📚 Credits

  • Based on a project from Python Simplified
  • Interface designed using Tkinter
  • Model trained using TensorFlow/Keras

About

Image classifier desktop app using TensorFlow and Tkinter. Upload an image and get predictions with confidence scores.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages