CLIP Representation Enhanced Predicate Estimation
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
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.
- Short Name / Acronym:
- CREPE
- Site Accession Number:
- LLNL-CODE-853963
- Software Type:
- Scientific
- License(s):
- MIT License
- Research Organization:
- Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA)Primary Award/Contract Number:AC52-07NA27344
- DOE Contract Number:
- AC52-07NA27344
- Code ID:
- 128865
- OSTI ID:
- code-128865
- Country of Origin:
- United States
Similar Records
DECIDER
Double Visual Defense
Software
·
Thu Sep 19 20:00:00 EDT 2024
·
OSTI ID:code-156111
Double Visual Defense
Software
·
Wed Dec 11 19:00:00 EST 2024
·
OSTI ID:code-154189