---
title: The DogID App
emoji: 🦮
colorFrom: green
colorTo: indigo
sdk: streamlit
sdk_version: 1.35.0
app_file: app.py
pinned: false
license: mit
short_description: An AI model that predicts the breed of a dog from an image
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference


# 🐶 The DogID App

Welcome to **The DogID App** — a fast and fun way to identify dog breeds using deep learning. Just upload a dog image and our app will predict the most likely breed out of 120 possibilities.

## 🚀 How it works

This app uses a fine-tuned MobileNetV2 deep learning model trained on the [Kaggle dog breed identification dataset](https://www.kaggle.com/competitions/dog-breed-identification/data) and powered by TensorFlow and Streamlit.

## 📦 Features

- 📸 Upload your own dog photo
- 🧠 Real-time breed predictions
- 🌐 Deployed on Hugging Face Spaces
- 🎨 Light mode enforced for consistent visuals

## 🛠️ Built With

- Python 🐍
- TensorFlow / Keras
- Streamlit
- Hugging Face Spaces

## 📂 File Overview

- `app.py` – Streamlit app script
- `requirements.txt` – Python dependencies
- `.streamlit/config.toml` – Forces light mode
- `dog_breed_ID_batch32_cache_prefetch.keras` – Trained model
- `assets/` – Logo and image files

## 📝 License

This project is licensed under the MIT License — see `LICENSE` file for details.

---

Enjoy using **The DogID App**! 🐾