SqueezeBrains SDK 1.13
|
SVL parameters that configure the Shallow Learning training, it wraps the sb_t_svl_sl_par structure More...
#include <cs_par.h>
Data Fields | |
String | network_path |
Network weights file path with extension SB_DL_WEIGHTS_EXT. More... | |
SbSvlDlParNetwork | network |
Network parameters. More... | |
int | pre_trained |
The network is loaded as pre-trained, i.e. network parameters are not randomly initialized before training but they start from a pre-existing configuration. More... | |
SbSvlDlParPerturbation | perturbations |
Perturbations for deep learning training. More... | |
float | learning_rate |
Learning rate. More... | |
int | num_epochs |
Number of epochs. More... | |
int | batch_size |
Size of the batch used during SVL. More... | |
float | validation_percentage |
Validation percentage. More... | |
int | save_best |
At the end of the training, the best internal parameters configuration is recovered. More... | |
SbSize | tile_factor |
Number of horizontal and vertical tiles used to process the image. More... | |
int | auto_tiling |
Enable the automatic tiling for image processing. More... | |
SbSizeFlt | scale |
Scale to applied to the image before the processing. More... | |
SbLossFnType | loss_fn |
Loss function. More... | |
SVL parameters that configure the Shallow Learning training, it wraps the sb_t_svl_sl_par structure
int sb_cs::SbSvlDlPar::auto_tiling |
Enable the automatic tiling for image processing.
int sb_cs::SbSvlDlPar::batch_size |
Size of the batch used during SVL.
float sb_cs::SbSvlDlPar::learning_rate |
SbLossFnType sb_cs::SbSvlDlPar::loss_fn |
SbSvlDlParNetwork sb_cs::SbSvlDlPar::network |
String sb_cs::SbSvlDlPar::network_path |
Network weights file path with extension SB_DL_WEIGHTS_EXT.
int sb_cs::SbSvlDlPar::num_epochs |
SbSvlDlParPerturbation sb_cs::SbSvlDlPar::perturbations |
Perturbations for deep learning training.
int sb_cs::SbSvlDlPar::pre_trained |
The network is loaded as pre-trained, i.e. network parameters are not randomly initialized before training but they start from a pre-existing configuration.
int sb_cs::SbSvlDlPar::save_best |
At the end of the training, the best internal parameters configuration is recovered.
SbSizeFlt sb_cs::SbSvlDlPar::scale |
Scale to applied to the image before the processing.
SbSize sb_cs::SbSvlDlPar::tile_factor |
Number of horizontal and vertical tiles used to process the image.
float sb_cs::SbSvlDlPar::validation_percentage |
Validation percentage.