https://github.com/wangleihitcs/captionmetrics
Image Caption metrics: Bleu、Cider、Meteor、Rouge、Spice
https://github.com/wangleihitcs/captionmetrics
bleu cider image-caption-metrics meteor rouge spice
Last synced: 17 days ago
JSON representation
Image Caption metrics: Bleu、Cider、Meteor、Rouge、Spice
- Host: GitHub
- URL: https://github.com/wangleihitcs/captionmetrics
- Owner: wangleihitcs
- Created: 2018-06-22T09:27:35.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-03-02T14:44:44.000Z (about 6 years ago)
- Last Synced: 2025-04-05T01:51:15.183Z (about 1 month ago)
- Topics: bleu, cider, image-caption-metrics, meteor, rouge, spice
- Language: Python
- Homepage:
- Size: 92.8 MB
- Stars: 111
- Watchers: 0
- Forks: 28
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
## introduce
Image Caption Metrics: Bleu、Cider、Meteor、Rouge、Spice## library
* python3.5 or python2.7
* jdk-1.8
* Stanford CoreNLP 3.6.0[(download)](http://nlp.stanford.edu/software/stanford-corenlp-full-2015-12-09.zip)
* add stanford-corenlp-3.6.0.jar to pycocoevalcap/spice/lib/
* add stanford-corenlp-3.6.0-models.jar to pycocoevalcap/spice/lib/## examples
- $ python main.py
## reference
* [https://github.com/tylin/coco-caption](https://github.com/tylin/coco-caption)## e.g
There is some thing wrong in python3, but python2 is right.
Fix the problem 'cider = 0 when only one image caption'.