Aidge backend OpenCV API

Databases

MNIST

C++

class MNIST : public Aidge::Database

Public Types

enum DataType

Values:

enumerator Unsigned

enumerator Signed

enumerator Short

enumerator Int

enumerator Float

enumerator Double

Public Functions

inline MNIST(const std::string &dataPath, bool train, bool loadDataInMemory = false)

Data Transformations.

~MNIST() noexcept

virtual std::vector<std::shared_ptr<Tensor>> getItem(const std::size_t index) const final override

Fetch an item of the database.

Parameters:

index – index of the item.

Returns:

vector of data mapped to index.

inline virtual std::size_t getLen() const noexcept final override

Get the number of items in the database.

Returns:

std::size_t

inline virtual std::size_t getNbModalities() const noexcept final override

Get the number of modalities in one database item.

Returns:

std::size_t

union MagicNumber

Public Members

std::uint32_t value

std::uint8_t byte[4]

Python

class aidge_backend_opencv.MNIST

__init__(self: aidge_backend_opencv.aidge_backend_opencv.MNIST, dataPath: str, train: bool, load_data_in_memory: bool = False) → None

get_item(self: aidge_backend_opencv.aidge_backend_opencv.MNIST, index: int) → List[aidge_core.aidge_core.Tensor]

Return samples of each data modality for the given index.

Parameters:

index (int) – Database index corresponding to one item

get_len(self: aidge_backend_opencv.aidge_backend_opencv.MNIST) → int

Return the number of items in the database.

get_nb_modalities(self: aidge_backend_opencv.aidge_backend_opencv.MNIST) → int

Return the number of modalities in one item of the database.

len(self: aidge_core.aidge_core.Database) → int

UTILS

std::shared_ptr<Tensor> Aidge::tensorOpencv(cv::Mat mat)

Instanciate an aidge tensor with backend “opencv” from an opencv matrix.

Parameters:

mat – the cv::mat to instanciate the tensor from

Returns:

std::shared_ptr<Tensor> aidge tensor