ozancaglayan / coco-caption

A Python 3 fork of the original coco-caption repository

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Microsoft COCO Caption Evaluation

Evaluation codes for MS COCO caption generation. This repository is a Python 3.x version of the original 2.x codebase

Changes

Requirements

  • JAVA Runtime
  • Python 3.x

Files

./cocoeval: Standalone evaluation script

./annotation

  • captions_val2014.json (MS COCO 2014 caption validation set)
  • Visit MS COCO download page for more details.

./results

  • captions_val2014_fakecap_results.json (an example of fake results for running demo)
  • Visit MS COCO format page for more details.

./pycocoevalcap: The folder where all evaluation codes are stored.

  • evals.py: The file includes COCOEvalCap class that can be used to evaluate results on COCO.
  • tokenizer: Python wrapper of Stanford CoreNLP PTBTokenizer
  • bleu: Bleu evalutation codes
  • meteor: Meteor evaluation codes
  • rouge: Rouge-L evaluation codes
  • cider: CIDEr evaluation codes
  • spice: SPICE evaluation codes

Setup

  • You will first need to download the Stanford CoreNLP 3.6.0 code and models for use by SPICE. To do this, run: ./get_stanford_models.sh
  • Note: SPICE will try to create a cache of parsed sentences in ./pycocoevalcap/spice/cache/. This dramatically speeds up repeated evaluations. The cache directory can be moved by setting 'CACHE_DIR' in ./pycocoevalcap/spice. In the same file, caching can be turned off by removing the '-cache' argument to 'spice_cmd'.

References

Developers

  • Xinlei Chen (CMU)
  • Hao Fang (University of Washington)
  • Tsung-Yi Lin (Cornell)
  • Ramakrishna Vedantam (Virgina Tech)

Acknowledgement

  • David Chiang (University of Norte Dame)
  • Michael Denkowski (CMU)
  • Alexander Rush (Harvard University)

About

A Python 3 fork of the original coco-caption repository

License:Other


Languages

Language:Jupyter Notebook 92.0%Language:Python 7.9%Language:Shell 0.1%