dl::utils::Dataset< T > Class Template Reference

#include <data_loader.hpp>

Public Member Functions
	Dataset ()
	Default constructor for empty dataset.
	Dataset (const MatrixD &features, const MatrixD &labels)
	Constructor with feature and label matrices.
void	add_sample (const std::vector< T > &feature, const std::vector< T > &label)
	Add a single sample to the dataset.
size_t	size () const
	Get the number of samples in the dataset.
std::pair< MatrixD, MatrixD >	get_batch (size_t start_idx, size_t batch_size) const
	Extract a batch of samples from the dataset.
void	shuffle ()
	Randomly shuffle the dataset samples.

Detailed Description

template<typename T>
class dl::utils::Dataset< T >

Definition at line 52 of file data_loader.hpp.

Constructor & Destructor Documentation

Dataset() [1/2]

template<typename T >

dl::utils::Dataset< T >::Dataset

(

)

Default constructor for empty dataset.

Examples

/home/runner/work/deep-learning-algo-impls/deep-learning-algo-impls/include/utils/data_loader.hpp.

Definition at line 15 of file data_loader.cpp.

Dataset() [2/2]

template<typename T >

dl::utils::Dataset< T >::Dataset	(	const MatrixD &	features,
		const MatrixD &	labels
	)

Constructor with feature and label matrices.

Parameters

features	Matrix containing input features (samples x features)
labels	Matrix containing target labels (samples x outputs)

Note

Features and labels must have the same number of rows (samples)

Definition at line 18 of file data_loader.cpp.

Member Function Documentation

add_sample()

template<typename T >

void dl::utils::Dataset< T >::add_sample	(	const std::vector< T > &	feature,
		const std::vector< T > &	label
	)

Add a single sample to the dataset.

Parameters

feature	Feature vector for the sample
label	Label vector for the sample

Note

This method dynamically grows the dataset

Examples

/home/runner/work/deep-learning-algo-impls/deep-learning-algo-impls/include/utils/data_loader.hpp.

Definition at line 26 of file data_loader.cpp.

get_batch()

template<typename T >

std::pair< MatrixD, MatrixD > dl::utils::Dataset< T >::get_batch	(	size_t	start_idx,
		size_t	batch_size
	)		const

Extract a batch of samples from the dataset.

Parameters

start_idx	Starting index for the batch
batch_size	Number of samples in the batch

Returns

Pair of (features, labels) matrices for the batch

Note

If start_idx + batch_size exceeds dataset size, returns samples from start_idx to the end

Examples

/home/runner/work/deep-learning-algo-impls/deep-learning-algo-impls/include/utils/data_loader.hpp.

Definition at line 38 of file data_loader.cpp.

shuffle()

template<typename T >

void dl::utils::Dataset< T >::shuffle

(

)

Randomly shuffle the dataset samples.

Note

Maintains correspondence between features and labels

Examples

/home/runner/work/deep-learning-algo-impls/deep-learning-algo-impls/include/utils/data_loader.hpp.

Definition at line 52 of file data_loader.cpp.

size()

template<typename T >

size_t dl::utils::Dataset< T >::size

(

)

const

Get the number of samples in the dataset.

Returns

Number of samples

Examples

/home/runner/work/deep-learning-algo-impls/deep-learning-algo-impls/include/utils/data_loader.hpp.

Definition at line 32 of file data_loader.cpp.

---

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

• include/utils/data_loader.hpp
• src/utils/data_loader.cpp