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

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

.. _sphx_glr_auto_examples_plot_load_and_predict.py:


.. _l-example-simple-usage:

Load and predict with ONNX Runtime and a very simple model
==========================================================

This example demonstrates how to load a model and compute
the output for an input vector. It also shows how to
retrieve the definition of its inputs and outputs.



.. code-block:: python


    import onnxruntime as rt
    import numpy
    from onnxruntime.datasets import get_example







Let's load a very simple model.
The model is available on github `onnx...test_sigmoid <https://github.com/onnx/onnx/tree/master/onnx/backend/test/data/node/test_sigmoid>`_.



.. code-block:: python


    example1 = get_example("sigmoid.onnx")
    sess = rt.InferenceSession(example1)







Let's see the input name and shape.



.. code-block:: python


    input_name = sess.get_inputs()[0].name
    print("input name", input_name)
    input_shape = sess.get_inputs()[0].shape
    print("input shape", input_shape)
    input_type = sess.get_inputs()[0].type
    print("input type", input_type)





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

 Out:

 .. code-block:: none

    input name x
    input shape [3, 4, 5]
    input type tensor(float)


Let's see the output name and shape.



.. code-block:: python


    output_name = sess.get_outputs()[0].name
    print("output name", output_name)  
    output_shape = sess.get_outputs()[0].shape
    print("output shape", output_shape)
    output_type = sess.get_outputs()[0].type
    print("output type", output_type)





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

 Out:

 .. code-block:: none

    output name y
    output shape [3, 4, 5]
    output type tensor(float)


Let's compute its outputs (or predictions if it is a machine learned model).



.. code-block:: python


    import numpy.random
    x = numpy.random.random((3,4,5))
    x = x.astype(numpy.float32)
    res = sess.run([output_name], {input_name: x})
    print(res)




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

 Out:

 .. code-block:: none

    [array([[[0.61738354, 0.5889719 , 0.6793853 , 0.50794476, 0.6481656 ],
            [0.63874   , 0.6554151 , 0.70349395, 0.7234402 , 0.5136753 ],
            [0.5245013 , 0.6156528 , 0.5979552 , 0.50427085, 0.6905146 ],
            [0.50659853, 0.5972322 , 0.63199735, 0.52700824, 0.5550221 ]],

           [[0.6085912 , 0.60911506, 0.5874832 , 0.62220854, 0.52513546],
            [0.6714244 , 0.554621  , 0.54446864, 0.50728863, 0.58585966],
            [0.69436765, 0.6819202 , 0.5424466 , 0.63762194, 0.7102783 ],
            [0.5940473 , 0.6690069 , 0.6540941 , 0.5415039 , 0.5430267 ]],

           [[0.70212066, 0.60011494, 0.613671  , 0.6573008 , 0.6949564 ],
            [0.5501859 , 0.65843284, 0.56367683, 0.5267073 , 0.50210917],
            [0.5226443 , 0.6559813 , 0.62244976, 0.690172  , 0.58052164],
            [0.55922556, 0.70860493, 0.72129   , 0.5805169 , 0.5123959 ]]],
          dtype=float32)]


**Total running time of the script:** ( 0 minutes  0.035 seconds)


.. _sphx_glr_download_auto_examples_plot_load_and_predict.py:


.. only :: html

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



  .. container:: sphx-glr-download

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



  .. container:: sphx-glr-download

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


.. only:: html

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

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