faninsar.samplers.ColSampler#

class faninsar.samplers.ColSampler(dataset: GeoDataset, roi: BoundingBox | None = None, col_num: int | None = None, width: int | None = None, verbose: bool = True)[source]#

Bases: PatchSampler

A sampler samples data from a dataset in a col-wise manner.

This class is used to sample data from a dataset. The dataset is represented by a bounding box, and the sampler is used to sample data in the bounding box. The result of sampling is an iterator that yields data from the dataset.

__init__(dataset: GeoDataset, roi: BoundingBox | None = None, col_num: int | None = None, width: int | None = None, verbose: bool = True) → None[source]#

Initialize a ColSampler.

Parameters:

  • dataset (GeoDataset) – The dataset needs to be sampled.

  • roi (BoundingBox or Sequence, optional) – The the region of interest bounding box. If not provided, the bounding box of the dataset will be used.

  • col_num (int, optional) – The number of patches to be sampled for row-wise sampling. If width is provided, this parameter will be ignored.

  • width (int, optional) – The width (in pixel) of the patch to be sampled for col-wise sampling. if not provided, the col_num will be used.

  • verbose (bool, optional) – Whether to print verbose information. The verbose of the dataset will be set to this value. Default is True.

Methods

__init__(dataset[, roi, col_num, width, verbose])

Initialize a ColSampler.

Attributes

boxes

The bounding boxes/patches of the sampler used to sample dataset.

shape

The shape of the patch sampler.
property boxes: ndarray#

The bounding boxes/patches of the sampler used to sample dataset.

property shape: tuple[int]#

The shape of the patch sampler.