🌍 Scene Classification Web App

A simple Streamlit web app that classifies uploaded images into six scene categories using a Vision Transformer (ViT).

The model has been trained to classify the following scene types:

• 🏙️ Buildings
• 🌲 Forest
• 🏔️ Glacier
• ⛰️ Mountain
• 🌊 Sea
• 🛣️ Street

---

🚀 Features

• Upload any .jpg, .jpeg, or .png image.
• The model predicts the scene category.
• Displays probabilities for all six classes in a bar chart.
• Shows the top prediction with confidence score.

---

🛠️ Tech Stack

• PyTorch – Model training and inference
• timm – Vision Transformer implementation
• Streamlit – Web app interface
• Matplotlib – Visualization

---

📦 Installation

Clone this repository:

git clone https://github.com/CodeNinjaSarthak/Landmark_Detection.git
cd Landmark_Detection

python -m venv venv
source venv/bin/activate   # On Linux/Mac
venv\Scripts\activate      # On Windows

pip install -r requirements.txt
streamlit run app.py

📜 License

This project is released under the MIT License. Feel free to use and modify it for your own projects