class chainer.datasets.ImageDataset(paths, root='.', dtype=<type 'numpy.float32'>)[source]

Dataset of images built from a list of paths to image files.

This dataset reads an external image file on every call of the __getitem__() operator. The paths to the image to retrieve is given as either a list of strings or a text file that contains paths in distinct lines.

Each image is automatically converted to arrays of shape channels, height, width, where channels represents the number of channels in each pixel (e.g., 1 for grey-scale images, and 3 for RGB-color images).


This dataset requires the Pillow package being installed. In order to use this dataset, install Pillow (e.g. by using the command pip install Pillow). Be careful to prepare appropriate libraries for image formats you want to use (e.g. libpng for PNG images, and libjpeg for JPG images).


You are responsible for preprocessing the images before feeding them to a model. For example, if your dataset contains both RGB and grayscale images, make sure that you convert them to the same format. Otherwise you will get errors because the input dimensions are different for RGB and grayscale images.

  • paths (str or list of strs) – If it is a string, it is a path to a text file that contains paths to images in distinct lines. If it is a list of paths, the i-th element represents the path to the i-th image. In both cases, each path is a relative one from the root path given by another argument.
  • root (str) – Root directory to retrieve images from.
  • dtype – Data type of resulting image arrays.



Returns an example or a sequence of examples.

It implements the standard Python indexing and one-dimensional integer array indexing. It uses the get_example() method by default, but it may be overridden by the implementation to, for example, improve the slicing performance.

Parameters:index (int, slice, list or numpy.ndarray) – An index of an example or indexes of examples.
Returns:If index is int, returns an example created by get_example. If index is either slice or one-dimensional list or numpy.ndarray, returns a list of examples created by get_example.


>>> import numpy
>>> from chainer import dataset
>>> class SimpleDataset(dataset.DatasetMixin):
...     def __init__(self, values):
...         self.values = values
...     def __len__(self):
...         return len(self.values)
...     def get_example(self, i):
...         return self.values[i]
>>> ds = SimpleDataset([0, 1, 2, 3, 4, 5])
>>> ds[1]   # Access by int
>>> ds[1:3]  # Access by slice
[1, 2]
>>> ds[[4, 0]]  # Access by one-dimensional integer list
[4, 0]
>>> index = numpy.arange(3)
>>> ds[index]  # Access by one-dimensional integer numpy.ndarray
[0, 1, 2]