VQA-CLIP: Amplifying CLIP-based Cross-Domain VQA via Enriched Scene Graphs
- Introduction
- Features
- Requirements
- Installation
- Configuration
- Training
- Folder Structure
- Contributing
- License
This is the repo for the VQA-CLIP: Amplifying CLIP-based Cross-Domain VQA via Enriched Scene Graphs
- Introducing Commonsense knowledge to cross-domain VQA task
- Attention between the nodes of the scene graph and question tokens.
- Python 3.7
- PyTorch
- Pytorch geometric
- Clip
-
Clone the repository:
git clone https://github.com/yourusername/yourproject.git cd yourproject
-
Install the dependencies:
pip install -r requirements.txt