Visual Question Answer

This project leverages transformers for question answering based on an uploaded image. The user interface (UI) is built using Gradio, providing an easy-to-use platform for interacting with the system.

Key Features:

• Upload an image.
• Ask a question related to the uploaded image.
• The system processes the input and returns an accurate answer.

How It Works:

1. Upload an image through the Gradio UI.
2. Type your question about the image.
3. The system analyzes both the image and the question, then provides an answer.

Installation

To get started with the project, follow these steps:

1. Clone the repository and navigate to the project directory:

   git clone https://github.com/arnabsroy9/Visual-Question-Answer.git
   cd Visual-Question-Answer

2. Install the required dependencies:

   pip install -r requirements.txt
   

Your environment is now ready!

Inference

To run, open the terminal in the Visual-Question-Answer/app directory and execute the following command:

python main.py

Output preview