.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "build/examples_depth/demo_monodepth2.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

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

        Click :ref:`here <sphx_glr_download_build_examples_depth_demo_monodepth2.py>`
        to download the full example code

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

.. _sphx_glr_build_examples_depth_demo_monodepth2.py:

01. Predict depth from a single image with pre-trained Monodepth2 models
===========================================================================

This is a quick demo of using GluonCV Monodepth2 model for KITTI on real-world images.
Please follow the `installation guide <../../index.html#installation>`__
to install MXNet and GluonCV if not yet.

.. GENERATED FROM PYTHON SOURCE LINES 8-17

.. code-block:: default

    import numpy as np

    import mxnet as mx
    from mxnet.gluon.data.vision import transforms
    import gluoncv
    # using cpu
    ctx = mx.cpu(0)









.. GENERATED FROM PYTHON SOURCE LINES 18-22

Prepare the image
-----------------

Let's first download the example image,

.. GENERATED FROM PYTHON SOURCE LINES 22-28

.. code-block:: default


    url = 'https://raw.githubusercontent.com/KuangHaofei/GluonCV_Test/master/monodepthv2/tutorials/test_img.png'
    filename = 'test_img.png'
    gluoncv.utils.download(url, filename, True)






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

 Out:

 .. code-block:: none

    Downloading test_img.png from https://raw.githubusercontent.com/KuangHaofei/GluonCV_Test/master/monodepthv2/tutorials/test_img.png...

      0%|          | 0/728 [00:00<?, ?KB/s]
    729KB [00:00, 58393.29KB/s]            




.. GENERATED FROM PYTHON SOURCE LINES 29-30

Then we load the image and visualize it,

.. GENERATED FROM PYTHON SOURCE LINES 30-38

.. code-block:: default


    import PIL.Image as pil
    img = pil.open(filename).convert('RGB')

    from matplotlib import pyplot as plt
    plt.imshow(img)
    plt.show()




.. image-sg:: /build/examples_depth/images/sphx_glr_demo_monodepth2_001.png
   :alt: demo monodepth2
   :srcset: /build/examples_depth/images/sphx_glr_demo_monodepth2_001.png
   :class: sphx-glr-single-img





.. GENERATED FROM PYTHON SOURCE LINES 39-41

We resize the image make it has the same input size with pretrained model,
and transfer the image to NDArray,

.. GENERATED FROM PYTHON SOURCE LINES 41-49

.. code-block:: default


    original_width, original_height = img.size
    feed_height = 192
    feed_width = 640

    img = img.resize((feed_width, feed_height), pil.LANCZOS)
    img = transforms.ToTensor()(mx.nd.array(img)).expand_dims(0).as_in_context(context=ctx)








.. GENERATED FROM PYTHON SOURCE LINES 50-54

Load the pre-trained model and make prediction
----------------------------------------------

Next, we get a pre-trained model from our model zoo,

.. GENERATED FROM PYTHON SOURCE LINES 54-58

.. code-block:: default


    model = gluoncv.model_zoo.get_model('monodepth2_resnet18_kitti_stereo_640x192',
                                        pretrained_base=False, ctx=ctx, pretrained=True)





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

 Out:

 .. code-block:: none

    Downloading /root/.mxnet/models/monodepth2_resnet18_kitti_stereo_640x192-83eea4a9.zip from https://apache-mxnet.s3-accelerate.dualstack.amazonaws.com/gluon/models/monodepth2_resnet18_kitti_stereo_640x192-83eea4a9.zip...

      0%|          | 0/70343 [00:00<?, ?KB/s]
      0%|          | 98/70343 [00:00<01:27, 801.78KB/s]
      1%|          | 514/70343 [00:00<00:30, 2317.41KB/s]
      3%|3         | 2178/70343 [00:00<00:09, 7357.90KB/s]
     12%|#1        | 8210/70343 [00:00<00:02, 25582.76KB/s]
     22%|##1       | 15318/70343 [00:00<00:01, 40577.04KB/s]
     34%|###3      | 23586/70343 [00:00<00:00, 52791.09KB/s]
     44%|####4     | 31075/70343 [00:00<00:00, 59610.49KB/s]
     55%|#####5    | 38785/70343 [00:00<00:00, 64958.78KB/s]
     67%|######7   | 47340/70343 [00:00<00:00, 68967.64KB/s]
     78%|#######8  | 55029/70343 [00:01<00:00, 71312.58KB/s]
     90%|######### | 63469/70343 [00:01<00:00, 75200.27KB/s]
    70344KB [00:01, 55337.75KB/s]                           




.. GENERATED FROM PYTHON SOURCE LINES 59-60

We directly make disparity map predictions on the image, and resize it to input size

.. GENERATED FROM PYTHON SOURCE LINES 60-65

.. code-block:: default


    outputs = model.predict(img)
    disp = outputs[("disp", 0)]
    disp_resized = mx.nd.contrib.BilinearResize2D(disp, height=original_height, width=original_width)








.. GENERATED FROM PYTHON SOURCE LINES 66-67

In the end, we add normalized color map for visualizing the predicted disparity map,

.. GENERATED FROM PYTHON SOURCE LINES 67-82

.. code-block:: default


    import matplotlib as mpl
    import matplotlib.cm as cm
    disp_resized_np = disp_resized.squeeze().as_in_context(mx.cpu()).asnumpy()
    vmax = np.percentile(disp_resized_np, 95)
    normalizer = mpl.colors.Normalize(vmin=disp_resized_np.min(), vmax=vmax)
    mapper = cm.ScalarMappable(norm=normalizer, cmap='magma')
    colormapped_im = (mapper.to_rgba(disp_resized_np)[:, :, :3] * 255).astype(np.uint8)
    im = pil.fromarray(colormapped_im)
    im.save('test_output.png')

    import matplotlib.image as mpimg
    disp_map = mpimg.imread('test_output.png')
    plt.imshow(disp_map)
    plt.show()



.. image-sg:: /build/examples_depth/images/sphx_glr_demo_monodepth2_002.png
   :alt: demo monodepth2
   :srcset: /build/examples_depth/images/sphx_glr_demo_monodepth2_002.png
   :class: sphx-glr-single-img






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

   **Total running time of the script:** ( 0 minutes  2.807 seconds)


.. _sphx_glr_download_build_examples_depth_demo_monodepth2.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: demo_monodepth2.py <demo_monodepth2.py>`



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

     :download:`Download Jupyter notebook: demo_monodepth2.ipynb <demo_monodepth2.ipynb>`


.. only:: html

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

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