williamcfrancis/Visual-Question-Answering-using-Stacked-Attention-Networks

Pytorch implementation of VQA using Stacked Attention Networks: Multimodal architecture for image and question input, using CNN and LSTM, with stacked attention layer for improved accuracy (54.82%). Includes visualization of attention layers. Contributions welcome. Utilizes Visual VQA v2.0 dataset.

Jupyter NotebookApache-2.0