Data

Tools

Indexes

Applications

Experiments

Open Source Science

nlp

NLP project from Paris-Dauphine University lecture. This project is aimed to predict Dataset captions using the "show and tell" approach developped by Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan.

https://github.com/naimlehbiben/nlp

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.8%) to scientific vocabulary

Keywords

caption-generation machine-learning nlp
Last synced: 10 months ago · JSON representation ·

Repository

NLP project from Paris-Dauphine University lecture. This project is aimed to predict Dataset captions using the "show and tell" approach developped by Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan.

Basic Info
  • Host: GitHub
  • Owner: NaimLehbiben
  • License: mit
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 14.8 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
caption-generation machine-learning nlp
Created about 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

Flickr 8k dataset captions prediction

Project goals

We address the problem of image captioning, which involves describing the visual content of an image with a sentence in natural language. We will implement a simplified version of the "show and tell" approach developped by Oriol Vinyals, Alexander Toshev, Samy Bengio, and Dumitru Erhan.

Setting up the project

Run the file following commands, it will install dependencies and create a virtual environment for the project : In Windows : bat python -m venv .venv @REM Could also be python3 -m venv .venv .\.venv\Scripts\pip.exe install -r requirements.txt In Linux/MacOS ```bash python -m venv .venv

Could also be python3 -m venv .venv

..venv\bin\pip install -r requirements.txt -U `` All the code is in thesrcfolder. The project guidelines are in thestatic` folder.

License

MIT

Authors

Authors: Naïm Lehbiben - Baptiste Zloch - Matthieu Monnot

Owner

  • Name: Naïm Lehbiben
  • Login: NaimLehbiben
  • Kind: user
  • Location: Paris
  • Company: Paris Dauphine University

Passionate about quantitative finance and trading I'm an ambitious and motivated young professional with a strong background in finance and mathematics.

Citation (CITATION) 

cff-version: 1.2.0
message: If you use this software, please cite it using the following DOI.
title: Flickr 8k dataset captions prediction
authors:
  - name: NAÏM LEHBIBEN
    email: naim.lehbiben@dauphine.eu
  - name:  BAPTISTE ZLOCH
    email: baptiste.zloch@dauphine.eu
  - name:  MATTHIEU MONNOT
    email: matthieu.monnot@dauphine.eu
license: MIT

GitHub Events

Total
Last Year

Dependencies

requirements.txt pypi
  • black *
  • ipykernel *
  • matplotlib *
  • nltk *
  • numpy *
  • pandas *
  • requests *
  • scikit-learn *
  • seaborn *
  • tensorflow *
  • tqdm *