Hi,
This repository contains my work for the final project of the EEE - 443: Neural Networks course at Bilkent University.
In our project, we explore models designed for image captioning. We use multiple encoder-decoder (injection, merge) models as well as an attention model, in order to determine the better architecture for this particular task. The final paper can be accessed here: https://xmassmx.github.io/Image-Captioning/
Note: Please do not copy this work and stay away from plagiarism. The work in this repository is my solution and is meant to be used as a guide only.