chainer.datasets.get_svhn(withlabel=True, scale=1.0, dtype=None, label_dtype=<class 'numpy.int32'>, add_extra=False)[source]

Gets the SVHN dataset.

The Street View House Numbers (SVHN) dataset is a dataset similar to MNIST but composed of cropped images of house numbers. The functionality of this function is identical to the counterpart for the MNIST dataset (get_mnist()), with the exception that there is no ndim argument.


SciPy is required to use this feature.

  • withlabel (bool) – If True, it returns datasets with labels. In this case, each example is a tuple of an image and a label. Otherwise, the datasets only contain images.

  • scale (float) – Pixel value scale. If it is 1 (default), pixels are scaled to the interval [0, 1].

  • dtype – Data type of resulting image arrays. chainer.config.dtype is used by default (see Configuring Chainer).

  • label_dtype – Data type of the labels.

  • add_extra – Use extra training set.


If add_extra is False, a tuple of two datasets (train and test). Otherwise, a tuple of three datasets (train, test, and extra). If withlabel is True, all datasets are TupleDataset instances. Otherwise, both datasets are arrays of images.