📘 CNN-Image-Classification-System

This is a simple machine learning prediction API built using Python, Flask, and a trained ML model.
It allows you to send data through Postman and receive prediction results instantly.

🚀 Features

• Simple and lightweight Flask API
• Accepts image input through Postman
• Returns model prediction in real time.
• Includes example request + response
• Easy to deploy and extend

📁 Project Structure

/project
│── models
|   |── Cats_Dogs_IMG_Classification_2.ipynb
|   |── final_model.keras
│── main.py
│── requirements.txt
│── README.md
│── License

🧰 Technologies Used

• Python – Core development
• Flask – Web application framework
• Tensorflow, NumPy – Data processing & ML model training
• Matplotlib – Interactive plots
• Keras – Model & metadata storage

⚙️ Installation & Setup

1. Clone the repository:

   git clone https://github.com/YourUsername/CNN-Image-Classification-System.git
   cd CNN-Image-Classification-System

2. Create virtual environment (optional but recommended):

   python -m venv venv
   venv\Scripts\activate   # For Windows
   # OR
   source venv/bin/activate  # For macOS/Linux

3. Install dependencies:

   pip install -r requirements.txt

4. Run the Flask server:

   python main.py

Server will start at: 👉 http://127.0.0.1:5000

📬 How to Use Postman for Prediction

Step 1 — Open Postman

• Download from: https://www.postman.com/downloads/
• Open the Postman app

Step 2 — Create a new POST request

1. Click New → HTTP Request
2. Select POST
3. Enter your API URL: http://127.0.0.1:5000/predict

Step 3 — Upload Image

• In Postman: Body → form-data

• Add the following key–value pair:

  KEY	TYPE	VALUE
  file	File	(choose an image file)

  • Key must be exactly: file
  • Type must be: File
  • Allowed formats: .jpg, .jpeg, .png

Step 4 — Send Request & Get Response

Click Send and you’ll receive a prediction similar to:

  {
    "prediction": "dog",
    "confidence": 0.9123
  }

or

  {
  "prediction": "cat",
  "confidence": 0.7344
  }

📄 Requirements

See requirements.txt for exact package versions.

🤝 Contribution

Pull requests are welcome! For major changes, please open an issue first to discuss what you'd like to improve.

📜 License

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