DeepBench: A simulation package for physical benchmarking data
- Fermilab
- Fermilab; Chicago U.; MIT, LNS
We introduce **DeepBench**, a python library that generates simple simulated image data from first principles, such as basic geometric shapes and astronomical objects. These data are highly valuable for developing (calibration, testing, and benchmarking) statistical and machine learning models because they make it possible to connect the final data product to physically interpretable inputs. This software includes tools to curate and store the datasets to maximize reproducibility.
- Research Organization:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States); Chicago U.; MIT, LNS
- Sponsoring Organization:
- US Department of Energy
- DOE Contract Number:
- 89243024CSC000002
- OSTI ID:
- 1989920
- Report Number(s):
- FERMILAB-FN-1231-CSAID; oai:inspirehep.net:2672814
- Country of Publication:
- United States
- Language:
- English
Similar Records
Assessing and benchmarking the fidelity of posterior inference methods for astrophysics data analysis
deeplenstronomy: A dataset simulation package for strong gravitational lensing
Scientific machine learning benchmarks
Conference
·
Tue Jan 16 23:00:00 EST 2024
·
OSTI ID:2282454
deeplenstronomy: A dataset simulation package for strong gravitational lensing
Journal Article
·
Wed Feb 03 23:00:00 EST 2021
· Journal of Open Source Software
·
OSTI ID:1764837
Scientific machine learning benchmarks
Journal Article
·
Wed Apr 06 00:00:00 EDT 2022
· Nature Reviews Physics
·
OSTI ID:1877481