Converts a scikit-learn model

The gallery of sklearn-onnx provides many examples with scikit-learn. The following takes the same example and rewrites it with onnxmltools.

Train and deploy a model usually involves the three following steps:

• train a pipeline with scikit-learn,

• convert it into ONNX with sklearn-onnx,

• predict with onnxruntime.

Train a model

A very basic example using random forest and the iris dataset.

import numpy
import onnx
import sklearn
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
import onnxruntime as rt

import skl2onnx
import onnxmltools
from onnxconverter_common.data_types import FloatTensorType
from onnxmltools.convert import convert_sklearn

iris = load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y)
clr = RandomForestClassifier()
clr.fit(X_train, y_train)
print(clr)

Out:

RandomForestClassifier()

Convert a model into ONNX

initial_type = [('float_input', FloatTensorType([None, 4]))]
onx = convert_sklearn(clr, initial_types=initial_type)

with open("rf_iris.onnx", "wb") as f:
    f.write(onx.SerializeToString())

Compute the prediction with onnxruntime

sess = rt.InferenceSession("rf_iris.onnx")
input_name = sess.get_inputs()[0].name
label_name = sess.get_outputs()[0].name
pred_onx = sess.run(
    [label_name], {input_name: X_test.astype(numpy.float32)})[0]
print(pred_onx)

Out:

[1 1 0 1 0 2 2 0 1 1 2 1 2 2 1 1 1 2 2 2 2 0 2 2 0 0 1 1 0 0 2 1 1 0 0 0 2
 1]

Full example with a logistic regression

clr = LogisticRegression()
clr.fit(X_train, y_train)
initial_type = [('float_input', FloatTensorType([None, X_train.shape[1]]))]
onx = convert_sklearn(clr, initial_types=initial_type)
with open("logreg_iris.onnx", "wb") as f:
    f.write(onx.SerializeToString())

sess = rt.InferenceSession("logreg_iris.onnx")
input_name = sess.get_inputs()[0].name
label_name = sess.get_outputs()[0].name
pred_onx = sess.run([label_name],
                    {input_name: X_test.astype(numpy.float32)})[0]
print(pred_onx)

Out:

somewhereonnxmltools-jenkins_39_std/_venv/lib/python3.9/site-packages/sklearn/linear_model/_logistic.py:814: ConvergenceWarning: lbfgs failed to converge (status=1):
STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.

Increase the number of iterations (max_iter) or scale the data as shown in:
    https://scikit-learn.org/stable/modules/preprocessing.html
Please also refer to the documentation for alternative solver options:
    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
  n_iter_i = _check_optimize_result(
[1 2 0 1 0 2 2 0 1 1 2 1 2 2 1 1 1 2 2 2 2 0 2 2 0 0 2 1 0 0 2 1 1 0 0 0 2
 1]

Display the ONNX graph

Finally, let’s see the graph converted with onnxmltools.

import os
import matplotlib.pyplot as plt
from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer

pydot_graph = GetPydotGraph(
    onx.graph, name=onx.graph.name, rankdir="TB",
    node_producer=GetOpNodeProducer(
        "docstring", color="yellow", fillcolor="yellow", style="filled"))
pydot_graph.write_dot("model.dot")

os.system('dot -O -Gdpi=300 -Tpng model.dot')

image = plt.imread("model.dot.png")
fig, ax = plt.subplots(figsize=(40, 20))
ax.imshow(image)
ax.axis('off')

Out:

(-0.5, 1982.5, 2558.5, -0.5)

Versions used for this example

print("numpy:", numpy.__version__)
print("scikit-learn:", sklearn.__version__)
print("onnx: ", onnx.__version__)
print("onnxruntime: ", rt.__version__)
print("onnxmltools: ", onnxmltools.__version__)
print("skl2onnx: ", skl2onnx.__version__)

Out:

numpy: 1.21.4
scikit-learn: 1.1.dev0
onnx:  1.10.2
onnxruntime:  1.10.91
onnxmltools:  1.10.0
skl2onnx:  1.10.4