pysegcnn.core.dataset.Cloud95Dataset¶
-
class
pysegcnn.core.dataset.
Cloud95Dataset
(root_dir, use_bands=[], tile_size=None, pad=False, gt_pattern='(.*)gt\\.tif', sort=False, seed=0, transforms=[])[source]¶ Class for the Cloud-95 dataset by Mohajerani & Saeedi (2020).
-
__init__
(root_dir, use_bands=[], tile_size=None, pad=False, gt_pattern='(.*)gt\\.tif', sort=False, seed=0, transforms=[])[source]¶ Initialize.
- Parameters
- root_dirstr
The root directory, path to the dataset.
- use_bandslist [str], optional
A list of the spectral bands to use. The default is [].
- tile_sizeint or None, optional
The size of the tiles. If not None, each scene is divided into square tiles of shape
(tile_size, tile_size)
. The default is None.- padbool, optional
Whether to center pad the input image. Set
pad=True
, if the images are not evenly divisible by thetile_size
. The image data is padded with a constant padding value of zero. For each image, the corresponding ground truth image is padded with a “no data” label. The default is False.- gt_patternstr, optional
A regural expression to match the ground truth naming convention. All directories and subdirectories in
root_dir
are searched for files matchinggt_pattern
. The default is (.*)gt\.tif.- sortbool, optional
Whether to chronologically sort the samples. Useful for time series data. The default is False.
- seedint, optional
The random seed. Used to split the dataset into training, validation and test set. Useful for reproducibility. The default is 0.
- transformslist, optional
List of
pysegcnn.core.transforms.Augment
instances. Each item intransforms
generates a distinct transformed version of the dataset. The total dataset is composed of the original untransformed dataset together with each transformed version of it. Iftransforms=[]
, only the original dataset is used. The default is [].
Methods
__init__
(root_dir[, use_bands, tile_size, …])Initialize.
build_samples
(scene)Stack the bands of a sample in a single array.
compose_scenes
()Build the list of samples of the dataset.
get_labels
()Class labels of the Cloud-95 dataset.
get_sensor
()Landsat 8 bands of the Cloud-95 dataset.
get_size
()Image size of the Cloud-95 dataset.
parse_scene_id
(scene_id)Parse Sparcs scene identifiers (Landsat 8).
preprocess
(data, gt)Preprocess Cloud-95 dataset images.
read_scene
(idx)Read the data of the sample with index
idx
.to_tensor
(x, dtype)Convert
x
totorch.Tensor
.-