Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/88705
Title: | Let me see: diseño de un generador automático de descripciones de imágenes |
Author: | Bengoechea Isasa, José Ignacio |
Director: | Casas-Roma, Jordi |
Tutor: | Bosch Rue, Anna |
Abstract: | The objective of this work is to design and implement a deep learning model to generate image captionings trough a encoder-decoder framework. This model will be evaluated with BLEU and ROUGE metrics, and an integration in Telegram will be carried out. |
Keywords: | convolutional neural network computer vision image processing deep learning |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | Jan-2019 |
Publication license: | https://creativecommons.org/licenses/by-nc-sa/3.0/es/ |
Appears in Collections: | Bachelor thesis, research projects, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
jbengoecheaiTFM0119.zip | Código fuente del TFM | 8,84 kB | Unknown | View/Open |
jbengoecheaiTFM0119presentacion.odp | Presentación del TFM | 45,14 MB | OpenDocument Presentation | View/Open |
jbengoecheaiTFM0119memoria.pdf | Memoria del TFM | 1,61 MB | Adobe PDF | View/Open |
Share:
This item is licensed under a Creative Commons License