pulsatrix 1.1.0
Loading...
Searching...
No Matches
pulsatrix::TemperatureFit Struct Reference

A fitted temperature and the weighted mean log loss before and after it. More...

#include <calibration.hpp>

Public Attributes

double temperature = 1.0
 
double log_loss_before = 0.0
 at T = 1
 
double log_loss_after = 0.0
 at the fitted T
 
int64_t iterations = 0
 
bool converged = true
 False when the minimum is at a bound of T in [1e-6, 1e6]: the loss keeps falling as T grows (the logits are no better than chance, or point the wrong way) or as T shrinks (the logits separate the labels perfectly). temperature is then that bound.
 

Detailed Description

A fitted temperature and the weighted mean log loss before and after it.

Member Data Documentation

◆ converged

bool pulsatrix::TemperatureFit::converged = true

False when the minimum is at a bound of T in [1e-6, 1e6]: the loss keeps falling as T grows (the logits are no better than chance, or point the wrong way) or as T shrinks (the logits separate the labels perfectly). temperature is then that bound.

◆ iterations

int64_t pulsatrix::TemperatureFit::iterations = 0

◆ log_loss_after

double pulsatrix::TemperatureFit::log_loss_after = 0.0

at the fitted T

◆ log_loss_before

double pulsatrix::TemperatureFit::log_loss_before = 0.0

at T = 1

◆ temperature

double pulsatrix::TemperatureFit::temperature = 1.0

The documentation for this struct was generated from the following file: