SB SDK 1.11
sb_t_svl_res_level Struct Reference

Results of the SVL of a level per model. More...

#include <sb.h>

Collaboration diagram for sb_t_svl_res_level:

Data Fields

float goodness
 Goodness of the training. More...
 
float accuracy
 Accuracy. More...
 
float score
 Level score. More...
 
int tp
 Number of TRUE POSITIVE samples. More...
 
int fp
 Number of FALSE POSITIVE samples. More...
 
int tn
 Number of TRUE NEGATIVE samples. More...
 
int fn
 Number of FALSE NEGATIVE samples. More...
 
int op
 Number of OPTIONAL POSITIVE samples. More...
 
int on
 Number of OPTIONAL NEGATIVE samples. More...
 
int out_of_roi
 Number of Out Of ROI samples, both optional and required. More...
 
int mod_disabled
 Number of samples with disabled model, both optional and required. More...
 
int reset
 1 if the SVL of the model has been resetted or when the user reset the SVL, 0 otherwise. More...
 
int num_samples_l
 Number of samples of the training dataset used for learning. More...
 
int num_samples_t
 Number of samples of the training dataset not used for learning. More...
 
int num_img_l
 Number of images of the training dataset used for learning.
 
sb_t_svl_par_optimization_mode optimization_mode
 Optimization mode. More...
 
char classificator [32]
 Classificator choosen by SVL. More...
 
char features [SB_PAR_FEATURES_NAMES_LEN]
 List of the features choosen by SVL. More...
 
char features_available [SB_PAR_FEATURES_NAMES_LEN]
 List of the features choosen by user for SVL. More...
 
char * warning
 Warning in string format occurred during the training.
 
sb_t_svl_res_epochs epochs
 Results of training of module based on Deep Learning. More...
 

Detailed Description

Results of the SVL of a level per model.

For a Retina project you could write that:

  • num_samples_l + num_samples_t = tp + fn + out_of_roi

While for a Surface project you could write that:

  • num_samples_l + num_samples_t = tp + fn + tn + out_of_roi

These two formulas are true only if there are no optional out_of_roi samples.
Usually, in Retina project, num_samples_t should be very small if compared to num_samples_l, on the contrary, in Surface projects, num_samples_t is very large because it also counts the background samples, i.e. True Negative samples.

Definition at line 11537 of file sb.h.

Field Documentation

◆ accuracy

float sb_t_svl_res_level::accuracy

Accuracy.

Definition at line 11553 of file sb.h.

◆ classificator

char sb_t_svl_res_level::classificator[32]

Classificator choosen by SVL.

Used only by Retina and Surface projects.

Definition at line 11627 of file sb.h.

◆ epochs

sb_t_svl_res_epochs sb_t_svl_res_level::epochs

Results of training of module based on Deep Learning.

Used only by Deep Surface and Deep Cortex projects.

Definition at line 11648 of file sb.h.

◆ features

char sb_t_svl_res_level::features[SB_PAR_FEATURES_NAMES_LEN]

List of the features choosen by SVL.

The features are separated by the SB_DELIMITER character.
Used only by Retina and Surface projects.

Definition at line 11633 of file sb.h.

◆ features_available

char sb_t_svl_res_level::features_available[SB_PAR_FEATURES_NAMES_LEN]

List of the features choosen by user for SVL.

The features are separated by the SB_DELIMITER character.
Used only by Retina and Surface projects.

Definition at line 11639 of file sb.h.

◆ fn

int sb_t_svl_res_level::fn

Number of FALSE NEGATIVE samples.

Used only by Retina and Surface projects.

Definition at line 11578 of file sb.h.

◆ fp

int sb_t_svl_res_level::fp

Number of FALSE POSITIVE samples.

Used only by Retina and Surface projects.

Definition at line 11568 of file sb.h.

◆ goodness

float sb_t_svl_res_level::goodness

Goodness of the training.

Used only by Retina and Surface projects.

Definition at line 11543 of file sb.h.

◆ mod_disabled

int sb_t_svl_res_level::mod_disabled

Number of samples with disabled model, both optional and required.

Used only by Retina and Surface projects.

Definition at line 11598 of file sb.h.

◆ num_samples_l

int sb_t_svl_res_level::num_samples_l

Number of samples of the training dataset used for learning.

Used only by Retina and Surface projects.

Definition at line 11608 of file sb.h.

◆ num_samples_t

int sb_t_svl_res_level::num_samples_t

Number of samples of the training dataset not used for learning.

Used only by Retina and Surface projects.

Definition at line 11613 of file sb.h.

◆ on

int sb_t_svl_res_level::on

Number of OPTIONAL NEGATIVE samples.

Used only by Retina and Surface projects.

Definition at line 11588 of file sb.h.

◆ op

int sb_t_svl_res_level::op

Number of OPTIONAL POSITIVE samples.

Used only by Retina and Surface projects.

Definition at line 11583 of file sb.h.

◆ optimization_mode

sb_t_svl_par_optimization_mode sb_t_svl_res_level::optimization_mode

Optimization mode.

Used only by Retina and Surface projects.

Definition at line 11622 of file sb.h.

◆ out_of_roi

int sb_t_svl_res_level::out_of_roi

Number of Out Of ROI samples, both optional and required.

Used only by Retina and Surface projects.

Definition at line 11593 of file sb.h.

◆ reset

int sb_t_svl_res_level::reset

1 if the SVL of the model has been resetted or when the user reset the SVL, 0 otherwise.

The value is valid only after sb_svl_run has been called and not after sb_project_load.

Definition at line 11603 of file sb.h.

◆ score

float sb_t_svl_res_level::score

Level score.

Used only by Surface project.

Definition at line 11558 of file sb.h.

◆ tn

int sb_t_svl_res_level::tn

Number of TRUE NEGATIVE samples.

Used only by Retina and Surface projects.

Definition at line 11573 of file sb.h.

◆ tp

int sb_t_svl_res_level::tp

Number of TRUE POSITIVE samples.

Used only by Retina and Surface projects.

Definition at line 11563 of file sb.h.


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