sb_t_svl_dl_par_network Struct Reference

Deep Learning modules parameters. More...

#include <sb.h>

Collaboration diagram for sb_t_svl_dl_par_network:

Data Fields
sb_t_network_type	type
	Network type. More...
sb_t_size	input_size
	Network input size. More...
sb_t_image_format	image_format
	Network input image format. More...
int	n_channels
	Deep Learning Network input channels. More...

Detailed Description

Deep Learning modules parameters.

Used only by Deep Cortex and Deep Surface projects.

Definition at line 8771 of file sb.h.

Field Documentation

image_format

sb_t_image_format sb_t_svl_dl_par_network::image_format

Network input image format.

Image format of the image that network expecting to elaborate. If the value is different from image format of the source image to be elaborated, the latter will be converted to be equal to the network one.
It is set to SB_IMAGE_FORMAT_RGB888 .

Warning

Readable only.

Definition at line 8809 of file sb.h.

input_size

sb_t_size sb_t_svl_dl_par_network::input_size

Network input size.

It determines, at which resolution, images must be resized before to be elaborated by the network. Each sb_t_svl_dl_par_network::type has its input size, which is fixed.

Warning

Readable only.

Definition at line 8800 of file sb.h.

n_channels

int sb_t_svl_dl_par_network::n_channels

Deep Learning Network input channels.

Number of input channels of the network. The value is directly related to sb_t_svl_dl_par_network::image_format.
It is set = 3.

Warning

Readable only.

Definition at line 8817 of file sb.h.

type

sb_t_network_type sb_t_svl_dl_par_network::type

Network type.

It specifies the Convolutional Neural Network (CNN) algorithm to be used by functions sb_svl_run and sb_project_detection.
Allowed values for Deep Cortex projects are:

• SB_NETWORK_TYPE_EFFICIENTNET_B0 , SB_NETWORK_TYPE_EFFICIENTNET_B1 , SB_NETWORK_TYPE_EFFICIENTNET_B2 : they all are different versions of the same base network EfficientNet in increasing order of performance, input resolution and computational complexity. EfficienNet is proved to perform well also on complex image classification tasks with limited training and inference time. More informations about EfficientNet are available in the official paper of the 2019: "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks" (https://arxiv.org/abs/1905.11946).
  
• SB_NETWORK_TYPE_ICNET0_64 , SB_NETWORK_TYPE_ICNET0_128 : they all are different versions of the the same base network ICNet (Image Classification Network) in increasing order of performance, input resolution and computational complexity. ICNet is a proprietary network designed by SqueezeBrains to solve efficiently simple and medium complex image classification vision tasks.
  

Allowed values for Deep Surface projects are:

• SB_NETWORK_TYPE_SDINET0_331 : SDINet (Surface Defect Inspection Network) is a proprietary network designed by SqueezeBrains to solve efficiently object/defect segmentation tasks. At the moment it works with a fixed input resolution equal to 331x331, i.e. images are all resized to those dimension before to be elaborated.
  In order to train on and detect small defects instances in images at higher resolution try to increase the tile factor .

Definition at line 8792 of file sb.h.

---

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

• sb.h