CUB2011

class pygmtools.dataset.CUB2011(sets, obj_resize, **ds_dict)[source]

Download and preprocess CUB2011 dataset.

Parameters

  • sets – str, problem set, 'train' for training set and 'test' for testing set

  • obj_resize – tuple, resized image size

  • ds_dict –

    settings of dataset, containing at most 2 params(keys) for CUB2011:

    • ROOT_DIR: str, directory of data

    • 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-(size, size).json for preprocessed dataset, train.json for training set, and test.json for testing set.