ecvl::GenerateClassificationDataset Class Reference

Generate an ecvl::Dataset from a directory tree for a classification task. More...

#include <dataset_generator.h>

Inheritance diagram for ecvl::GenerateClassificationDataset:

Public Member Functions
	GenerateClassificationDataset (const filesystem::path &dataset_root_directory)
	GenerateClassificationDataset constructor. More...
virtual int	LoadSplitImages (const filesystem::path &split) override
	Load the path of images and labels of the specified split. More...
Public Member Functions inherited from ecvl::GenerateDataset
	GenerateDataset (const filesystem::path &dataset_root_directory)
	GenerateDataset constructor. More...
virtual	~GenerateDataset ()=default
void	LoadImagesAndSplits ()
	Call LoadSplitImages and load the splits with indexes of corresponding images. More...
Dataset	GetDataset ()
	Return the Dataset object obtained from the directory structure. More...

Additional Inherited Members
Public Attributes inherited from ecvl::GenerateDataset
const filesystem::path	dataset_root_directory_
	path containing the root directory of the dataset More...
std::vector< std::string >	splits_
	vector containing the splits found in the dataset directory, if present More...
std::vector< int >	num_samples_
	vector containing the number of samples for each split More...
ecvl::Dataset	d_
	Dataset object to fill. More...

Detailed Description

Generate an ecvl::Dataset from a directory tree for a classification task.

Assumes a directory structure where a top-level directory can have subdirectories named "training", "validation" and "test" (possibly not all present), each of which has in turn one subdirectory for each class, containing the images for that class. For more detailed information about the supported directory structure check https://github.com/deephealthproject/ecvl/wiki/ECVL-Dataset-Generator.

Definition at line 121 of file dataset_generator.h.

Constructor & Destructor Documentation

GenerateClassificationDataset()

ecvl::GenerateClassificationDataset::GenerateClassificationDataset ( const filesystem::path &  dataset_root_directory )

inline

GenerateClassificationDataset constructor.

All the splits must have a directory for each class. If there aren't samples of that class, the directory has to be empty.

Parameters

[in]

dataset_root_directory

path containing the root directory of the dataset.

Definition at line 131 of file dataset_generator.h.

Member Function Documentation

LoadSplitImages()

virtual int ecvl::GenerateClassificationDataset::LoadSplitImages ( const filesystem::path &  split )

overridevirtual

Load the path of images and labels of the specified split.

Parameters

[in]

split

directory name of the split that we are considering.

Returns

The number of samples of the split.

Implements ecvl::GenerateDataset.

---

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

• dataset_generator.h