This project demonstrates how to deploy a FastAI-based image classification model into a web application using Flask. The web application classifies uploaded images into one of four categories: Pigeon, Dog, Adult, and Baby.
The primary goal of this project is to show the process of integrating a machine learning model into a Flask application. The model is a convolutional neural network (CNN) trained with the FastAI library. Flask, a lightweight web framework for Python, is used to create an interface between the user and the model.
- Clone the repository:
git clone https://github.com/Olney1/Image-Classification.git - Navigate to the project directory:
cd Image-Classification - Install the required packages:
pip install -r requirements.txt - Run the Flask application:
python app.py - Open your web browser and visit
localhost:5000to see the application in action.
The user uploads an image through the web interface. The image is then processed and fed into the neural network model. The model makes a prediction about the class of the image (Pigeon, Dog, Adult, Baby, or Unknown if the confidence score is below a certain threshold). The prediction, along with the associated confidence score, is then displayed on the webpage.
This project serves as a starting point and can be expanded to suit other use-cases. If you'd like to contribute, please feel free to make a pull request.
The current model is specifically trained to classify images into four categories. For more diverse or accurate results, the model should be retrained on a different dataset.