chainer.datasets.get_svhn¶
-
chainer.datasets.
get_svhn
(withlabel=True, scale=1.0, dtype=<class 'numpy.float32'>, label_dtype=<class 'numpy.int32'>)[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 nondim
argument.Note
SciPy is required to use this feature.
Parameters: - 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.
- label_dtype – Data type of the labels.
Returns: A tuple of two datasets. If
withlabel
isTrue
, both datasets areTupleDataset
instances. Otherwise, both datasets are arrays of images.- withlabel (bool) – If