You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Add multi-unit capabilities to numerical and categorical calibration layers.
Is your feature request related to a problem? Please describe.
As we build up the PyTorch Lattice Library, we will be implementing optimizations for the basic Lattice model which will require it to handle multiple units (RTL and Kronecker factored lattices). As a prerequisite, we will need the calibrators to accept multi-unit inputs.
Describe the solution you'd like
A refactoring of categorical_calibrator and numerical_calibrator classes to include multi unit functionality.
Describe alternatives you've considered
N/A
Additional context
N/A
The text was updated successfully, but these errors were encountered:
About:
Add multi-unit capabilities to numerical and categorical calibration layers.
Is your feature request related to a problem? Please describe.
As we build up the PyTorch Lattice Library, we will be implementing optimizations for the basic Lattice model which will require it to handle multiple units (RTL and Kronecker factored lattices). As a prerequisite, we will need the calibrators to accept multi-unit inputs.
Describe the solution you'd like
A refactoring of categorical_calibrator and numerical_calibrator classes to include multi unit functionality.
Describe alternatives you've considered
N/A
Additional context
N/A
The text was updated successfully, but these errors were encountered: