CUB2011

class pygmtools.dataset.CUB2011(sets, obj_resize, ds_dict=None, **args)[source]

This class is defined to download and preprocess CUB2011 dataset.

Parameters

  • sets – str, problem set, ‘train’ for training set and ‘test’ for test set

  • obj_resize – tuple, resized image size

  • ds_dict –

    settings of dataset, containing at most 1 param(key) for CUB2011:

    CLS_SPLIT: str, ‘ori’ (original split), ‘sup’ (super class) or ‘all’ (all birds as one class)

download(url=None)[source]

Automatically download CUB2011 dataset.

Parameters

url – str, web url of CUB2011

process()[source]

Process the dataset and generate ‘data.json’ for preprocessed dataset, ‘train.json’ for training set, and ‘test.json’ for test set.