Skip to content

In Memory Dataset

Source

In-memory dataset module.

InMemoryDataset

Bases: Dataset

Dataset storing data in memory and allowing generating patches from it.

Parameters:

  • data_config (CAREamics DataConfig) –

    (see careamics.config.data_model.DataConfig) Data configuration.

  • inputs (ndarray or list[Path]) –

    Input data.

  • input_target (ndarray or list[Path], default: None ) –

    Target data, by default None.

  • read_source_func (Callable, default: read_tiff ) –

    Read source function for custom types, by default read_tiff.

  • **kwargs (Any, default: {} ) –

    Additional keyword arguments, unused.

__getitem__(index)

Return the patch corresponding to the provided index.

Parameters:

  • index (int) –

    Index of the patch to return.

Returns:

  • tuple of numpy.ndarray –

    Patch.

Raises:

  • ValueError –

    If dataset mean and std are not set.

__init__(data_config, inputs, input_target=None, read_source_func=read_tiff, **kwargs)

Constructor.

Parameters:

  • data_config (GeneralDataConfig) –

    Data configuration.

  • inputs (ndarray or list[Path]) –

    Input data.

  • input_target (ndarray or list[Path], default: None ) –

    Target data, by default None.

  • read_source_func (Callable, default: read_tiff ) –

    Read source function for custom types, by default read_tiff.

  • **kwargs (Any, default: {} ) –

    Additional keyword arguments, unused.

__len__()

Return the length of the dataset.

Returns:

  • int –

    Length of the dataset.

get_data_statistics()

Return training data statistics.

This does not return the target data statistics, only those of the input.

Returns:

  • tuple of list of floats –

    Means and standard deviations across channels of the training data.

split_dataset(percentage=0.1, minimum_patches=1)

Split a new dataset away from the current one.

This method is used to extract random validation patches from the dataset.

Parameters:

  • percentage (float, default: 0.1 ) –

    Percentage of patches to extract, by default 0.1.

  • minimum_patches (int, default: 1 ) –

    Minimum number of patches to extract, by default 5.

Returns:

  • CAREamics InMemoryDataset –

    New dataset with the extracted patches.

Raises:

  • ValueError –

    If percentage is not between 0 and 1.

  • ValueError –

    If minimum_number is not between 1 and the number of patches.