Repository navigation
v2.0.0
This release:
- introduces conditional NetTrustScore (CNTS) that measures trustworthiness for true and false predictions for each class.
- simplifies the import and call processes, (Trustworthiness.compute_NTS() -> NTS.compute() and CNTS.compute())
- adds assert conditions,
- sets trust spectrum plot to False by default,
- adds plots.py for user interaction under assets,
- adds conditional_trust_densities.png under assets,
- has several minor bug fixes and cosmetic improvements