Skip to content

Latest commit

 

History

History
24 lines (14 loc) · 1018 Bytes

README.md

File metadata and controls

24 lines (14 loc) · 1018 Bytes

Visual Question Answering (MSc Project)

This repository contains the implementation of the proposed VQA model from my MSc project. The implementation was done using PyTorch and OpenVQA framework.

VQA Model

The main folder for the model is located here, and the main python file for the model is here.

VQA model

Visualisation

The code to generate visualisation of attention distribution is here.

Visualisation of model's attention distribution on image

vis-1va

Visualisation of model's attention distribution on text data

vis-1va