This project implements a Visual Question Answering (VQA) system using a pre-trained model from Hugging Face or a locally stored model.

Table of Contents

• Installation
• Usage
  • Using the Default Hugging Face Model (Online Mode)
  • Using a Local Model (Offline Mode)
  • Using an Image from a URL
  • Running the Streamlit App
• Running Tests Locally
• Contributing
• License

Installation

1. Clone the repository:

   git clone https://github.com/tedoaba/Vision-Question-Answering.git
   cd Vision-Question-Answering

2. Create a virtual environment:

   python -m venv venv
   source venv/Scripts/activate  # On Windows
   

3. Install the dependencies:

   pip install -r requirements.txt

Usage

Using the Default Hugging Face Model (Online Mode)

Run the VQA system with an image and a question:

python scripts/run_vqa.py --image "path_to_image.jpg" --question "What is the person doing?"

Using a Local Model (Offline Mode)

Run the VQA system with a local model:

python scripts/run_vqa.py --image "path_to_image.jpg" --question "What is the color of the car?" --model_path "models/vqa/"

Using an Image from a URL

Run the VQA system with an image URL:

python scripts/run_vqa.py --image "https://example.com/image.jpg" --question "What is happening in the image?" --url

Running the Streamlit App

To run the Streamlit app, use the following command:

streamlit run app.py

Running Tests Locally

To run the tests locally, follow these steps:

1. Install the dependencies:

   pip install -r requirements.txt

2. Run the tests:

   python -m unittest discover -s tests

Contributing

Contributions are welcome! Please open an issue or submit a pull request for any improvements or bug fixes.

License

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