.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "build/examples_datasets/cityscapes.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        Click :ref:`here <sphx_glr_download_build_examples_datasets_cityscapes.py>`
        to download the full example code

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_build_examples_datasets_cityscapes.py:

Prepare Cityscapes dataset.
========================

`Cityscapes <http://sceneparsing.csail.mit.edu/>`_  focuses on semantic understanding of
urban street scenes. This tutorial help you to download Cityscapes and set it up for later experiments.

.. image:: https://www.cityscapes-dataset.com/wordpress/wp-content/uploads/2015/07/stuttgart02-2040x500.png
   :width: 600 px


Prepare the dataset
-------------------


Please login and download the files `gtFine_trainvaltest.zip` and `leftImg8bit_trainvaltest.zip` to
the current folder:

+---------------------------------------+--------+
| File name                             | Size   |
+=======================================+========+
| gtFine_trainvaltest.zip               | 253 MB |
+---------------------------------------+--------+
| leftImg8bit_trainvaltest.zip          | 12 GB  |
+---------------------------------------+--------+

Then run this script:

 :download:`Download script: cityscapes.py<../../../scripts/datasets/cityscapes.py>`

.. code-block:: bash

   python cityscapes.py


.. GENERATED FROM PYTHON SOURCE LINES 37-42

How to load the dataset
-----------------------

Loading images and labels from Cityscapes is straight-forward
with GluonCV's dataset utility:

.. GENERATED FROM PYTHON SOURCE LINES 42-50

.. code-block:: default


    from gluoncv.data import CitySegmentation
    train_dataset = CitySegmentation(split='train')
    val_dataset = CitySegmentation(split='val')
    print('Training images:', len(train_dataset))
    print('Validation images:', len(val_dataset))






.. rst-class:: sphx-glr-script-out

 Out:

 .. code-block:: none

    Found 2975 images in the folder /root/.mxnet/datasets/citys/leftImg8bit/train
    Found 500 images in the folder /root/.mxnet/datasets/citys/leftImg8bit/val
    Training images: 2975
    Validation images: 500




.. GENERATED FROM PYTHON SOURCE LINES 51-54

Get the first sample
--------------------


.. GENERATED FROM PYTHON SOURCE LINES 54-62

.. code-block:: default

    import numpy as np
    img, mask = val_dataset[0]
    # get pallete for the mask
    from gluoncv.utils.viz import get_color_pallete
    mask = get_color_pallete(mask.asnumpy(), dataset='citys')
    mask.save('mask.png')









.. GENERATED FROM PYTHON SOURCE LINES 63-66

Visualize data and label
------------------------


.. GENERATED FROM PYTHON SOURCE LINES 66-79

.. code-block:: default

    from matplotlib import pyplot as plt
    import matplotlib.image as mpimg
    # subplot 1 for img
    fig = plt.figure()
    fig.add_subplot(1,2,1)
    plt.imshow(img.asnumpy().astype('uint8'))
    # subplot 2 for the mask
    mmask = mpimg.imread('mask.png')
    fig.add_subplot(1,2,2)
    plt.imshow(mmask)
    # display
    plt.show()




.. image-sg:: /build/examples_datasets/images/sphx_glr_cityscapes_001.png
   :alt: cityscapes
   :srcset: /build/examples_datasets/images/sphx_glr_cityscapes_001.png
   :class: sphx-glr-single-img






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** ( 0 minutes  10.063 seconds)


.. _sphx_glr_download_build_examples_datasets_cityscapes.py:


.. only :: html

 .. container:: sphx-glr-footer
    :class: sphx-glr-footer-example



  .. container:: sphx-glr-download sphx-glr-download-python

     :download:`Download Python source code: cityscapes.py <cityscapes.py>`



  .. container:: sphx-glr-download sphx-glr-download-jupyter

     :download:`Download Jupyter notebook: cityscapes.ipynb <cityscapes.ipynb>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_