🚀 CIFAR-10 Image Classifier

This is a Streamlit app running a TensorFlow/Keras CNN trained on the CIFAR-10 dataset.
Upload an image, and the model will predict one of 10 classes:

airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck

---

🌐 Live Demo (Hugging Face)

👉 Try it here:
https://huggingface.co/spaces/Pant0x/CNN

Runs fully in the browser. No setup required.

---

🧩 Features

• Upload images (PNG / JPG)
• Auto-resize and preprocess
• Predict top-3 classes with confidence scores
• Visualize all class probabilities in a bar chart
• Deployed and running on Hugging Face Spaces

---

📁 Project Structure

• app.py — Streamlit application
• models/cifar10_cnn.keras — Trained CNN model
• models/labels_map.json — Class label mapping
• requirements.txt — Python dependencies

---

⚡ Deployment

This app is deployed on Hugging Face Spaces using Streamlit.
Simply push the repository with this structure and Hugging Face will automatically build and host the app.

---

🧠 Model

• Dataset: CIFAR-10
• Framework: TensorFlow / Keras
• Architecture: Convolutional Neural Network (CNN)

---

Built for fast demos, clean inference, and easy deployment.