Published March 1, 2019
| Version v2
Dataset
Open
Look, Read and Enrich -Learning from Scientific Figures and their Captions - model weights and corpus
Description
This deposit contains the model weights and corpora used for executing the experiments of the paper Look, Read and Enrich -Learning from Scientific Figures and their Captions. The code is available here.
Jsons (jsons.zip):
- coco.json
- flickr30k.json
- scigraph.json
- semscholar.json
- tqa.json
- tqa_old.json
Models (saved.zip)
- modelCaptions_weights_FCC6.h5
- modelImages_weights_FCC6.h5
- modelImages_weights_FCC7.h5
Tokenizers (saved.zip)
- tokenizer-0-semscholar-FCC6.pickle
- tokenizer-0-semscholar-FCC7.pickle
Images (scigraph.zip, semscholar.zip, tqa.zip)
Files
jsons.zip
Files
(20.2 GB)
| Name | Size | Download all |
|---|---|---|
|
md5:33d9c172f6501847cc2b7c7012704891
|
90.6 MB | Preview Download |
|
md5:6794557483190e46b6e70eb8a9302c51
|
560.9 MB | Preview Download |
|
md5:5d3eaa491f285526eab577b2f7e797c5
|
2.7 GB | Preview Download |
|
md5:d1436d0819b3f648a0da5256cdb8a51a
|
16.5 GB | Preview Download |
|
md5:be6f40e8f671dd8c74f6bf50a725b52d
|
336.1 MB | Preview Download |