Let me see: an encoder-decoder image captioning
This repository is based on previous work of:
- Vinyals, O. T. (2015). Show and Tell: A neural image Caption generator. arXiv, 1411.4555.
- Tanti, M. G. (2018). Where to put the Image in an Image Caption Generator. arXiv:, 1703.09137.
Jose Ignacio Bengoechea Isasa, ignacio.bengis@gmail.com
- Language: Python 3.7.
- Requires tensorflow, keras, pillow, numpy, pandas.
Assuming git, python and pip installed:
git clone https://github.com/Bengis/Let-me-see
cd Let-me-see/code
python preprocessing.py
python encoder.py
python train.py
The dataset of this software is Flickr8K. You can request here to download the dataset.
- This software is part of the final proyect of the Master of Data Science
- Master of Data Science.
- Universitat Oberta of Catalunya.
- Tutored by: Anna Bosch Rué