Abstract
This software provides functions to perform visual predicate estimation by leveraging the pre-trained
vision-language model CLIP. In addition to training the prediction estimator with a labeled dataset, it also
performs performance evaluation and visualization of results.
- Developers:
-
Jayaraman Thiagarajan, Jayaraman [1]
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Release Date:
- 2023-07-21
- Project Type:
- Open Source, Publicly Available Repository
- Software Type:
- Scientific
- Version:
- 0.1
- Licenses:
-
MIT License
- Sponsoring Org.:
-
USDOE National Nuclear Security Administration (NNSA)Primary Award/Contract Number:AC52-07NA27344
- Code ID:
- 128865
- Site Accession Number:
- LLNL-CODE-853963
- Research Org.:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Country of Origin:
- United States
Citation Formats
Jayaraman Thiagarajan, Jayaraman.
CLIP Representation Enhanced Predicate Estimation.
Computer Software.
https://github.com/LLNL/CREPE.
USDOE National Nuclear Security Administration (NNSA).
21 Jul. 2023.
Web.
doi:10.11578/dc.20240614.257.
Jayaraman Thiagarajan, Jayaraman.
(2023, July 21).
CLIP Representation Enhanced Predicate Estimation.
[Computer software].
https://github.com/LLNL/CREPE.
https://doi.org/10.11578/dc.20240614.257.
Jayaraman Thiagarajan, Jayaraman.
"CLIP Representation Enhanced Predicate Estimation." Computer software.
July 21, 2023.
https://github.com/LLNL/CREPE.
https://doi.org/10.11578/dc.20240614.257.
@misc{
doecode_128865,
title = {CLIP Representation Enhanced Predicate Estimation},
author = {Jayaraman Thiagarajan, Jayaraman},
abstractNote = {This software provides functions to perform visual predicate estimation by leveraging the pre-trained
vision-language model CLIP. In addition to training the prediction estimator with a labeled dataset, it also
performs performance evaluation and visualization of results.},
doi = {10.11578/dc.20240614.257},
url = {https://doi.org/10.11578/dc.20240614.257},
howpublished = {[Computer Software] \url{https://doi.org/10.11578/dc.20240614.257}},
year = {2023},
month = {jul}
}