SVHN Data Set

class deepobs.pytorch.datasets.svhn.svhn(batch_size, data_augmentation=True, train_eval_size=26032)

DeepOBS data set class for the Street View House Numbers (SVHN) data set.

Parameters:

• batch_size (int) -- The mini-batch size to use. Note that, if batch_size is not a divider of the dataset size (73 000 for train, 26 000 for test) the remainder is dropped in each epoch (after shuffling).
• data_augmentation (bool) -- If True some data augmentation operations (random crop window, lighting augmentation) are applied to the training data (but not the test data).
• train_eval_size (int) -- Size of the train eval dataset. Defaults to 26 000 the size of the test set.