onnxruntime/python/_sources/auto_examples/plot_train_convert_predict.rst.txt

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

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

.. _sphx_glr_auto_examples_plot_train_convert_predict.py:



.. _l-logreg-example:

Train, convert and predict with ONNX Runtime
============================================

This example demonstrates an end to end scenario
starting with the training of a machine learned model
to its use in its converted from.

.. contents::
    :local:

Train a logistic regression
+++++++++++++++++++++++++++

The first step consists in retrieving the iris datset.



.. code-block:: python


    from sklearn.datasets import load_iris
    iris = load_iris()
    X, y = iris.data, iris.target

    from sklearn.model_selection import train_test_split
    X_train, X_test, y_train, y_test = train_test_split(X, y)







Then we fit a model.



.. code-block:: python


    from sklearn.linear_model import LogisticRegression
    clr = LogisticRegression()
    clr.fit(X_train, y_train)







We compute the prediction on the test set
and we show the confusion matrix.



.. code-block:: python

    from sklearn.metrics import confusion_matrix

    pred = clr.predict(X_test)
    print(confusion_matrix(y_test, pred))





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

 Out:

 .. code-block:: none

    [[ 9  0  0]
     [ 0 15  1]
     [ 0  1 12]]


Conversion to ONNX format
+++++++++++++++++++++++++

We use module 
`sklearn-onnx <https://github.com/onnx/sklearn-onnx>`_
to convert the model into ONNX format.



.. code-block:: python


    from skl2onnx import convert_sklearn
    from skl2onnx.common.data_types import FloatTensorType

    initial_type = [('float_input', FloatTensorType([None, 4]))]
    onx = convert_sklearn(clr, initial_types=initial_type)
    with open("logreg_iris.onnx", "wb") as f:
        f.write(onx.SerializeToString())







We load the model with ONNX Runtime and look at
its input and output.



.. code-block:: python


    import onnxruntime as rt
    sess = rt.InferenceSession("logreg_iris.onnx")

    print("input name='{}' and shape={}".format(
        sess.get_inputs()[0].name, sess.get_inputs()[0].shape))
    print("output name='{}' and shape={}".format(
        sess.get_outputs()[0].name, sess.get_outputs()[0].shape))





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

 Out:

 .. code-block:: none

    input name='float_input' and shape=[None, 4]
    output name='output_label' and shape=[1]


We compute the predictions.



.. code-block:: python


    input_name = sess.get_inputs()[0].name
    label_name = sess.get_outputs()[0].name

    import numpy
    pred_onx = sess.run([label_name], {input_name: X_test.astype(numpy.float32)})[0]
    print(confusion_matrix(pred, pred_onx))





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

 Out:

 .. code-block:: none

    [[ 9  0  0]
     [ 0 16  0]
     [ 0  0 13]]


The prediction are perfectly identical.

Probabilities
+++++++++++++

Probabilities are needed to compute other
relevant metrics such as the ROC Curve.
Let's see how to get them first with
scikit-learn.



.. code-block:: python


    prob_sklearn = clr.predict_proba(X_test)
    print(prob_sklearn[:3])





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

 Out:

 .. code-block:: none

    [[0.00198628 0.71308408 0.28492964]
     [0.00481246 0.83770353 0.15748401]
     [0.00483108 0.75930899 0.23585993]]


And then with ONNX Runtime.
The probabilies appear to be 



.. code-block:: python


    prob_name = sess.get_outputs()[1].name
    prob_rt = sess.run([prob_name], {input_name: X_test.astype(numpy.float32)})[0]

    import pprint
    pprint.pprint(prob_rt[0:3])





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

 Out:

 .. code-block:: none

    [{0: 0.0019862803164869547, 1: 0.7130840420722961, 2: 0.28492966294288635},
     {0: 0.0048124659806489944, 1: 0.8377037048339844, 2: 0.15748386085033417},
     {0: 0.004831086378544569, 1: 0.7593092322349548, 2: 0.23585963249206543}]


Let's benchmark.



.. code-block:: python

    from timeit import Timer

    def speed(inst, number=10, repeat=20):
        timer = Timer(inst, globals=globals())
        raw = numpy.array(timer.repeat(repeat, number=number))
        ave = raw.sum() / len(raw) / number
        mi, ma = raw.min() / number, raw.max() / number
        print("Average %1.3g min=%1.3g max=%1.3g" % (ave, mi, ma))
        return ave

    print("Execution time for clr.predict")
    speed("clr.predict(X_test)")

    print("Execution time for ONNX Runtime")
    speed("sess.run([label_name], {input_name: X_test.astype(numpy.float32)})[0]")





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

 Out:

 .. code-block:: none

    Execution time for clr.predict
    Average 4.8e-05 min=4.63e-05 max=5.71e-05
    Execution time for ONNX Runtime
    Average 3.19e-05 min=3.08e-05 max=3.81e-05


Let's benchmark a scenario similar to what a webservice
experiences: the model has to do one prediction at a time
as opposed to a batch of prediction.



.. code-block:: python


    def loop(X_test, fct, n=None):
        nrow = X_test.shape[0]
        if n is None:
            n = nrow
        for i in range(0, n):
            im = i % nrow
            fct(X_test[im: im+1])

    print("Execution time for clr.predict")
    speed("loop(X_test, clr.predict, 100)")

    def sess_predict(x):
        return sess.run([label_name], {input_name: x.astype(numpy.float32)})[0]

    print("Execution time for sess_predict")
    speed("loop(X_test, sess_predict, 100)")





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

 Out:

 .. code-block:: none

    Execution time for clr.predict
    Average 0.00445 min=0.00423 max=0.00495
    Execution time for sess_predict
    Average 0.00151 min=0.00145 max=0.00164


Let's do the same for the probabilities.



.. code-block:: python


    print("Execution time for predict_proba")
    speed("loop(X_test, clr.predict_proba, 100)")

    def sess_predict_proba(x):
        return sess.run([prob_name], {input_name: x.astype(numpy.float32)})[0]

    print("Execution time for sess_predict_proba")
    speed("loop(X_test, sess_predict_proba, 100)")





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

 Out:

 .. code-block:: none

    Execution time for predict_proba
    Average 0.00643 min=0.00632 max=0.00666
    Execution time for sess_predict_proba
    Average 0.00158 min=0.00152 max=0.00177


This second comparison is better as 
ONNX Runtime, in this experience,
computes the label and the probabilities
in every case.


Benchmark with RandomForest
+++++++++++++++++++++++++++

We first train and save a model in ONNX format.



.. code-block:: python

    from sklearn.ensemble import RandomForestClassifier
    rf = RandomForestClassifier()
    rf.fit(X_train, y_train)

    initial_type = [('float_input', FloatTensorType([1, 4]))]
    onx = convert_sklearn(rf, initial_types=initial_type)
    with open("rf_iris.onnx", "wb") as f:
        f.write(onx.SerializeToString())







We compare.



.. code-block:: python


    sess = rt.InferenceSession("rf_iris.onnx")

    def sess_predict_proba_rf(x):
        return sess.run([prob_name], {input_name: x.astype(numpy.float32)})[0]

    print("Execution time for predict_proba")
    speed("loop(X_test, rf.predict_proba, 100)")

    print("Execution time for sess_predict_proba")
    speed("loop(X_test, sess_predict_proba_rf, 100)")





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

 Out:

 .. code-block:: none

    Execution time for predict_proba
    Average 0.516 min=0.483 max=0.572
    Execution time for sess_predict_proba
    Average 0.00176 min=0.00171 max=0.00188


Let's see with different number of trees.



.. code-block:: python


    measures = []

    for n_trees in range(5, 51, 5):   
        print(n_trees)
        rf = RandomForestClassifier(n_estimators=n_trees)
        rf.fit(X_train, y_train)
        initial_type = [('float_input', FloatTensorType([1, 4]))]
        onx = convert_sklearn(rf, initial_types=initial_type)
        with open("rf_iris_%d.onnx" % n_trees, "wb") as f:
            f.write(onx.SerializeToString())
        sess = rt.InferenceSession("rf_iris_%d.onnx" % n_trees)
        def sess_predict_proba_loop(x):
            return sess.run([prob_name], {input_name: x.astype(numpy.float32)})[0]
        tsk = speed("loop(X_test, rf.predict_proba, 100)", number=5, repeat=5)
        trt = speed("loop(X_test, sess_predict_proba_loop, 100)", number=5, repeat=5)
        measures.append({'n_trees': n_trees, 'sklearn': tsk, 'rt': trt})

    from pandas import DataFrame
    df = DataFrame(measures)
    ax = df.plot(x="n_trees", y="sklearn", label="scikit-learn", c="blue", logy=True)
    df.plot(x="n_trees", y="rt", label="onnxruntime",
                    ax=ax, c="green", logy=True)
    ax.set_xlabel("Number of trees")
    ax.set_ylabel("Prediction time (s)")
    ax.set_title("Speed comparison between scikit-learn and ONNX Runtime\nFor a random forest on Iris dataset")
    ax.legend()



.. image:: /auto_examples/images/sphx_glr_plot_train_convert_predict_001.png
    :class: sphx-glr-single-img


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

 Out:

 .. code-block:: none

    5
    Average 0.042 min=0.0412 max=0.0432
    Average 0.00137 min=0.00136 max=0.00138
    10
    Average 0.065 min=0.0641 max=0.0662
    Average 0.00151 min=0.00139 max=0.00159
    15
    Average 0.0886 min=0.0873 max=0.0911
    Average 0.00145 min=0.00143 max=0.00148
    20
    Average 0.113 min=0.112 max=0.115
    Average 0.0015 min=0.00149 max=0.00152
    25
    Average 0.14 min=0.135 max=0.15
    Average 0.00161 min=0.0016 max=0.00164
    30
    Average 0.159 min=0.154 max=0.167
    Average 0.00149 min=0.00146 max=0.00158
    35
    Average 0.183 min=0.177 max=0.195
    Average 0.00153 min=0.0015 max=0.00159
    40
    Average 0.221 min=0.203 max=0.242
    Average 0.0019 min=0.00153 max=0.0024
    45
    Average 0.23 min=0.22 max=0.248
    Average 0.00177 min=0.00171 max=0.0018
    50
    Average 0.245 min=0.244 max=0.248
    Average 0.0016 min=0.00157 max=0.00165


**Total running time of the script:** ( 2 minutes  25.165 seconds)


.. _sphx_glr_download_auto_examples_plot_train_convert_predict.py:


.. only :: html

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



  .. container:: sphx-glr-download

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



  .. container:: sphx-glr-download

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


.. only:: html

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

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