CustomDataset Class Reference

This class allows loading a Custom Dataset in Libtorch. More...

#include <dataset.hpp>

Inheritance diagram for CustomDataset:

Public Member Functions
	CustomDataset (std::vector< std::string > list_images, std::vector< int > list_labels, int resize=224)
torch::data::Example	get (size_t index) override
void	show_batch (int grid_size=3)
	Visualize batch of data (by default 3x3) More...
void	show_sample (int index)
torch::optional< size_t >	size () const override

Detailed Description

Example Usage:

std::pair<std::vector<std::string>, std::vector<int>> pair_images_labels = load_data_from_folder(folders_name);
std::vector<std::string> list_images = pair_images_labels.first;
std::vector<int> list_labels = pair_images_labels.second;
auto custom_dataset = CustomDataset(list_images, list_labels, 64);

Constructor & Destructor Documentation

CustomDataset()

CustomDataset::CustomDataset ( std::vector< std::string >  list_images, std::vector< int >  list_labels, int  resize = 224  )

inline

Member Function Documentation

get()

torch::data::Example CustomDataset::get ( size_t  index )

inlineoverride

This should return {torch::Tensor, torch::Tensor}

Arguments:

1. index (type: size_t)

show_batch()

void CustomDataset::show_batch ( int  grid_size = 3 )

inline

Arguments:

1. grid_size (type: int, default = 3) Saves image in the build/ folder (name: out.jpg)

show_sample()

void CustomDataset::show_sample ( int  index )

inline

Visualizes sample at the given index

size()

torch::optional<size_t> CustomDataset::size ( ) const

inlineoverride

This function returns size of the dataset

---

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

• include/dataset.hpp