pugh_torch.datasets.segmentation package¶

Submodules¶

pugh_torch.datasets.segmentation.ade20k module¶

class pugh_torch.datasets.segmentation.ade20k.ADE20K(split='train', *, transform=None, **kwargs)[source]¶

Bases: pugh_torch.datasets.base.Dataset

Attempts to download data.

Parameters

split (str) – One of {“train”, “val”, “test”}. Which data partition to use. Case insensitive.
transform (obj) – Whatever format you want. Depends on dataset __getitem__ implementation. Defaults to just a ToTensor transform. This attribute is NOT used anywhere except in the dataset-specific __get__ implementation, or other parent classes of the dataset..

DOWNLOAD_URLS = [('http://data.csail.mit.edu/places/ADEchallenge/ADEChallengeData2016.zip', '219e1696abb36c8ba3a3afe7fb2f4b4606a897c7'), ('http://data.csail.mit.edu/places/ADEchallenge/release_test.zip', 'e05747892219d10e9243933371a497e905a4860c')]¶

PAYLOAD_NAMES = ['ADEChallengeData2016.zip', 'release_test.zip']¶

download()[source]¶

Function to download data to self.path.

The directories up to self.path have already been created.

Will only be called if data has not been downloaded.

unpack()[source]¶: Extract the downloaded zip files. No further processing required.

Module contents¶

pugh_torch.datasets.segmentation.__init__