- chainer.datasets.get_svhn(withlabel=True, scale=1.0, dtype=None, label_dtype=<class 'numpy.int32'>, add_extra=False)¶
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
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
dtype – Data type of resulting image arrays.
chainer.config.dtypeis used by default (see Configuring Chainer).
label_dtype – Data type of the labels.
add_extra – Use extra training set.
False, a tuple of two datasets (train and test). Otherwise, a tuple of three datasets (train, test, and extra). If
True, all datasets are
TupleDatasetinstances. Otherwise, both datasets are arrays of images.