SqueezeBrains SDK 1.13
sb_t_stat_model Struct Reference

Statistics of a model. More...

#include <sb.h>

Collaboration diagram for sb_t_stat_model:

Data Fields

int tp
 Count of True Positive. More...
int tn
 Count of True Negative. More...
int fp
 Count of False Positive. More...
int fn
 Count of False Negative. More...
int op
 Count of Optional Positive. More...
int on
 Count of Optional Negative. More...
int out_of_roi
 Count of Out Of ROI. More...
int mod_disabled
 Count of samples with model disabled. More...
sb_t_range_flt tp_weight
 Range of classification weight of the True Positive samples.
sb_t_range_flt tn_weight
 Range of classification weight of the True Negative samples.
sb_t_range_flt fp_weight
 Range of classification weight of the False Positive samples.
sb_t_range_flt fn_weight
 Range of classification weight of the False Negative samples.
sb_t_range_flt op_weight
 Range of classification weight of the Optional Positive samples.
sb_t_range_flt on_weight
 Range of classification weight of the Optional Negative samples.
sb_t_range_flt or_weight
 Range of classification weight of the out of the ROI samples.
float precision
 precision More...
float recall
 recall More...
float accuracy
 accuracy More...
float specificity
 specificity More...
float score
 Level score. More...

Detailed Description

Statistics of a model.

In multi-model case may happen that a FALSE NEGATIVE sample is associated with a FALSE POSITIVE sample. In this case the error weighs double in the statistics calculation.
See also

Definition at line 11397 of file sb.h.

Field Documentation

◆ accuracy

float sb_t_stat_model::accuracy


accuracy = (tp + tn) / (tp + tn + fp + fn)

Definition at line 11499 of file sb.h.

◆ fn

int sb_t_stat_model::fn

Count of False Negative.

Definition at line 11438 of file sb.h.

◆ fp

int sb_t_stat_model::fp

Count of False Positive.

Definition at line 11428 of file sb.h.

◆ mod_disabled

int sb_t_stat_model::mod_disabled

Count of samples with model disabled.

Definition at line 11474 of file sb.h.

◆ on

int sb_t_stat_model::on

Count of Optional Negative.

Definition at line 11457 of file sb.h.

◆ op

int sb_t_stat_model::op

Count of Optional Positive.

Definition at line 11448 of file sb.h.

◆ out_of_roi

int sb_t_stat_model::out_of_roi

Count of Out Of ROI.

Definition at line 11466 of file sb.h.

◆ precision

float sb_t_stat_model::precision


precision = tp / (tp + fp)

Definition at line 11487 of file sb.h.

◆ recall

float sb_t_stat_model::recall


recall = tp / (tp + fn)

Definition at line 11493 of file sb.h.

◆ score

float sb_t_stat_model::score

Level score.

Score of the model on the processed level. It is computed only in SVL mode.
The range of the values is [0, 1]
Used only with Surface projects.

Definition at line 11513 of file sb.h.

◆ specificity

float sb_t_stat_model::specificity


specificity = tn / (tn + fp)

Definition at line 11505 of file sb.h.

◆ tn

int sb_t_stat_model::tn

Count of True Negative.

  • Retina: count of True Negative samples. Moreover, the value is set to 1 if an image has no samples and no occurrences have been found.
  • Surface, Deep Surface: count of True Negative blobs if blob analysis has been performed.
  • Deep Cortex: count of True Negative images.

Definition at line 11418 of file sb.h.

◆ tp

int sb_t_stat_model::tp

Count of True Positive.

Definition at line 11407 of file sb.h.

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