.. only:: html

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

        Click :ref:`here <sphx_glr_download_Examples_1_TensorflowExample.py>`     to download the full example code
    .. rst-class:: sphx-glr-example-title

    .. _sphx_glr_Examples_1_TensorflowExample.py:


Tensorflow Example
====================

Top contributors (to current version):
  - Christopher Lazarus
  - Kyle Julian
  
This file is part of the Marabou project.
Copyright (c) 2017-2019 by the authors listed in the file AUTHORS
in the top-level source directory) and their institutional affiliations.
All rights reserved. See the file COPYING in the top-level source
directory for licensing information.


.. code-block:: default


    from maraboupy import Marabou
    import numpy as np


This network has inputs x0, x1, and was trained to create outputs that approximate
y0 = abs(x0) + abs(x1), y1 = x0^2 + x1^2


.. code-block:: default

    filename = "../../resources/tf/frozen_graph/fc1.pb"
    network = Marabou.read_tf(filename)


Or, you can specify the operation names of the input and output operations.
The default chooses the placeholder operations as input and the last operation as output


.. code-block:: default

    inputNames = ['Placeholder']
    outputName = 'y_out'
    network = Marabou.read_tf(filename = filename, inputNames = inputNames, outputName = outputName)


Get the input and output variable numbers; [0] since first dimension is batch size


.. code-block:: default

    inputVars = network.inputVars[0][0]
    outputVars = network.outputVars[0]


Set input bounds on both input variables


.. code-block:: default

    network.setLowerBound(inputVars[0],-10.0)
    network.setUpperBound(inputVars[0], 10.0)
    network.setLowerBound(inputVars[1],-10.0)
    network.setUpperBound(inputVars[1], 10.0)


Set output bounds on the second output variable


.. code-block:: default

    network.setLowerBound(outputVars[1], 194.0)
    network.setUpperBound(outputVars[1], 210.0)


Call to C++ Marabou solver


.. code-block:: default

    vals, stats = network.solve("marabou.log")

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

   **Total running time of the script:** ( 0 minutes  0.000 seconds)


.. _sphx_glr_download_Examples_1_TensorflowExample.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: 1_TensorflowExample.py <1_TensorflowExample.py>`



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

     :download:`Download Jupyter notebook: 1_TensorflowExample.ipynb <1_TensorflowExample.ipynb>`


.. only:: html

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

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