Python onnxruntime.__version__() Examples
The following are 30
code examples of onnxruntime.__version__().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
onnxruntime
, or try the search function
.
.
Example #1
| Source File: test_sklearn_tfidf_vectorizer_converter.py From sklearn-onnx with MIT License | 7 votes |
|
def test_model_tfidf_vectorizer11(self):
corpus = numpy.array([
"This is the first document.",
"This document is the second document.",
"And this is the third one.",
"Is this the first document?",
]).reshape((4, 1))
vect = TfidfVectorizer(ngram_range=(1, 1), norm=None)
vect.fit(corpus.ravel())
model_onnx = convert_sklearn(vect, "TfidfVectorizer",
[("input", StringTensorType())],
options=self.get_options())
self.assertTrue(model_onnx is not None)
dump_data_and_model(
corpus,
vect,
model_onnx,
basename="SklearnTfidfVectorizer11-OneOff-SklCol",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.4.0')",
)
sess = InferenceSession(model_onnx.SerializeToString())
res = sess.run(None, {'input': corpus.ravel()})[0]
assert res.shape == (4, 9)
Example #2
| Source File: test_sklearn_decision_tree_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_extra_tree_regressor_bool(self):
model, X = fit_regression_model(
ExtraTreeRegressor(random_state=42), is_bool=True)
model_onnx = convert_sklearn(
model,
"extra tree regressor",
[("input", BooleanTensorType([None, X.shape[1]]))],
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnExtraTreeRegressionBool-Dec4",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')")
Example #3
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_classifier_samme_r(self):
model, X_test = fit_classification_model(AdaBoostClassifier(
n_estimators=10, algorithm="SAMME.R", random_state=42,
base_estimator=DecisionTreeClassifier(
max_depth=2, random_state=42)), 3)
model_onnx = convert_sklearn(
model,
"AdaBoost classification",
[("input", FloatTensorType((None, X_test.shape[1])))],
target_opset=10
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X_test,
model,
model_onnx,
basename="SklearnAdaBoostClassifierSAMMER",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #4
| Source File: test_sklearn_calibrated_classifier_cv_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_model_calibrated_classifier_cv_binary(self):
data = load_iris()
X, y = data.data, data.target
y[y > 1] = 1
clf = MultinomialNB().fit(X, y)
model = CalibratedClassifierCV(clf, cv=2, method="sigmoid").fit(X, y)
model_onnx = convert_sklearn(
model,
"scikit-learn CalibratedClassifierCV",
[("input", FloatTensorType([None, X.shape[1]]))],
target_opset=TARGET_OPSET
)
self.assertTrue(model_onnx is not None)
dump_data_and_model(
X.astype(np.float32),
model,
model_onnx,
basename="SklearnCalibratedClassifierCVBinaryMNB",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #5
| Source File: test_sklearn_calibrated_classifier_cv_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_model_calibrated_classifier_cv_logistic_regression(self):
data = load_iris()
X, y = data.data, data.target
y[y > 1] = 1
model = CalibratedClassifierCV(
base_estimator=LogisticRegression(), method='sigmoid').fit(X, y)
model_onnx = convert_sklearn(
model, "unused",
[("input", FloatTensorType([None, X.shape[1]]))],
target_opset=TARGET_OPSET
)
self.assertTrue(model_onnx is not None)
dump_data_and_model(
X.astype(np.float32),
model,
model_onnx,
basename="SklearnCalibratedClassifierCVBinaryLogReg",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #6
| Source File: sphinx_keras2onnx_extension.py From keras-onnx with MIT License | 6 votes |
|
def kerasonnx_version_role(role, rawtext, text, lineno, inliner, options=None, content=None):
"""
Defines custom role *keras2onnx-version* which returns
*keras2onnx* version.
"""
if options is None:
options = {}
if content is None:
content = []
if text == 'v':
version = 'v' + keras2onnx.__version__
elif text == 'rt':
version = 'v' + onnxruntime.__version__
else:
raise RuntimeError("keras2onnx_version_role cannot interpret content '{0}'.".format(text))
node = nodes.Text(version)
return [node], []
Example #7
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_classifier_samme_r_decision_function(self):
model, X_test = fit_classification_model(AdaBoostClassifier(
n_estimators=10, algorithm="SAMME.R", random_state=42,
base_estimator=DecisionTreeClassifier(
max_depth=2, random_state=42)), 4)
options = {id(model): {'raw_scores': True}}
model_onnx = convert_sklearn(
model,
"AdaBoost classification",
[("input", FloatTensorType((None, X_test.shape[1])))],
target_opset=10,
options=options,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X_test,
model,
model_onnx,
basename="SklearnAdaBoostClassifierSAMMERDecisionFunction",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
methods=['predict', 'decision_function'],
)
Example #8
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_classifier_samme_r_logreg(self):
model, X_test = fit_classification_model(AdaBoostClassifier(
n_estimators=5, algorithm="SAMME.R",
base_estimator=LogisticRegression(
solver='liblinear')), 4)
model_onnx = convert_sklearn(
model,
"AdaBoost classification",
[("input", FloatTensorType((None, X_test.shape[1])))],
target_opset=10
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X_test,
model,
model_onnx,
basename="SklearnAdaBoostClassifierSAMMERLogReg",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #9
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_classifier_samme(self):
model, X_test = fit_classification_model(AdaBoostClassifier(
n_estimators=5, algorithm="SAMME", random_state=42,
base_estimator=DecisionTreeClassifier(
max_depth=6, random_state=42)), 2)
model_onnx = convert_sklearn(
model,
"AdaBoostClSamme",
[("input", FloatTensorType((None, X_test.shape[1])))],
target_opset=10,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X_test,
model,
model_onnx,
basename="SklearnAdaBoostClassifierSAMMEDT",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"< StrictVersion('0.5.0')",
)
Example #10
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_classifier_samme_decision_function(self):
model, X_test = fit_classification_model(AdaBoostClassifier(
n_estimators=5, algorithm="SAMME", random_state=42,
base_estimator=DecisionTreeClassifier(
max_depth=6, random_state=42)), 2)
options = {id(model): {'raw_scores': True}}
model_onnx = convert_sklearn(
model,
"AdaBoostClSamme",
[("input", FloatTensorType((None, X_test.shape[1])))],
target_opset=10,
options=options,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X_test,
model,
model_onnx,
basename="SklearnAdaBoostClassifierSAMMEDTDecisionFunction",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"< StrictVersion('0.5.0')",
methods=['predict', 'decision_function_binary'],
)
Example #11
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_classifier_bool(self):
model, X_test = fit_classification_model(
AdaBoostClassifier(random_state=42), 3,
is_bool=True)
model_onnx = convert_sklearn(
model,
"AdaBoost classification",
[("input", BooleanTensorType((None, X_test.shape[1])))],
target_opset=10,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X_test,
model,
model_onnx,
basename="SklearnAdaBoostClassifierBool",
allow_failure="StrictVersion("
"onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #12
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_regressor(self):
model, X = fit_regression_model(
AdaBoostRegressor(n_estimators=5))
model_onnx = convert_sklearn(
model, "AdaBoost regression",
[("input", FloatTensorType([None, X.shape[1]]))],
target_opset=10)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnAdaBoostRegressor-Dec4",
allow_failure="StrictVersion("
"onnxruntime.__version__) "
"< StrictVersion('0.5.0') or "
"StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')",
)
Example #13
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_regressor_lreg(self):
model, X = fit_regression_model(
AdaBoostRegressor(n_estimators=5,
base_estimator=LinearRegression()))
model_onnx = convert_sklearn(
model, "AdaBoost regression",
[("input", FloatTensorType([None, X.shape[1]]))],
target_opset=10)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnAdaBoostRegressorLReg-Dec4",
allow_failure="StrictVersion("
"onnxruntime.__version__) "
"< StrictVersion('0.5.0') or "
"StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')",
)
Example #14
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_regressor_int(self):
model, X = fit_regression_model(
AdaBoostRegressor(n_estimators=5), is_int=True)
model_onnx = convert_sklearn(
model, "AdaBoost regression",
[("input", Int64TensorType([None, X.shape[1]]))],
target_opset=10)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnAdaBoostRegressorInt-Dec4",
allow_failure="StrictVersion("
"onnxruntime.__version__) "
"< StrictVersion('0.5.0') or "
"StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')",
)
Example #15
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_regressor_lr10(self):
model, X = fit_regression_model(
AdaBoostRegressor(learning_rate=0.5, random_state=42))
model_onnx = convert_sklearn(
model, "AdaBoost regression",
[("input", FloatTensorType([None, X.shape[1]]))],
target_opset=10)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnAdaBoostRegressorLR-Dec4",
allow_failure="StrictVersion("
"onnxruntime.__version__) "
"< StrictVersion('0.5.0') or "
"StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')",
verbose=False
)
Example #16
| Source File: test_sklearn_adaboost_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_ada_boost_regressor_bool(self):
model, X = fit_regression_model(
AdaBoostRegressor(learning_rate=0.5, random_state=42),
is_bool=True)
model_onnx = convert_sklearn(
model, "AdaBoost regression",
[("input", BooleanTensorType([None, X.shape[1]]))],
target_opset=10,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnAdaBoostRegressorBool",
allow_failure="StrictVersion("
"onnxruntime.__version__) "
"< StrictVersion('0.5.0') or "
"StrictVersion(onnx.__version__) "
"== StrictVersion('1.4.1')",
verbose=False,
)
Example #17
| Source File: test_sklearn_glm_classifier_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_model_logistic_regression_binary_class(self):
model, X = fit_classification_model(
linear_model.LogisticRegression(max_iter=100), 2)
model_onnx = convert_sklearn(
model, "logistic regression",
[("input", FloatTensorType([None, X.shape[1]]))])
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnLogitisticRegressionBinary",
# Operator cast-1 is not implemented in onnxruntime
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.3') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')",
)
if StrictVersion(ort_version) >= StrictVersion("1.0.0"):
sess = InferenceSession(model_onnx.SerializeToString())
out = sess.get_outputs()
lb = out[0].type
sh = out[0].shape
self.assertEqual(str(lb), "tensor(int64)")
self.assertEqual(sh, [None])
Example #18
| Source File: test_sklearn_nearest_neighbour_converter.py From sklearn-onnx with MIT License | 6 votes |
|
def test_model_knn_multi_class_nocl(self):
model, X = fit_classification_model(
KNeighborsClassifier(),
2, label_string=True)
model_onnx = convert_sklearn(
model, "KNN multi-class nocl",
[("input", FloatTensorType([None, X.shape[1]]))],
options={id(model): {'nocl': True}},
target_opset=TARGET_OPSET)
self.assertIsNotNone(model_onnx)
sonx = str(model_onnx)
assert 'classlabels_strings' not in sonx
assert 'cl0' not in sonx
dump_data_and_model(
X, model, model_onnx, classes=model.classes_,
basename="SklearnKNNMultiNoCl", verbose=False,
allow_failure="StrictVersion(onnx.__version__)"
" < StrictVersion('1.2') or "
"StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')")
Example #19
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_binary_classification(self):
model, X = fit_classification_model(
GradientBoostingClassifier(n_estimators=3), 2)
model_onnx = convert_sklearn(
model,
"gradient boosting classifier",
[("input", FloatTensorType([None, X.shape[1]]))],
dtype=np.float32,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingBinaryClassifier",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #20
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_multiclass_classification(self):
model, X = fit_classification_model(
GradientBoostingClassifier(n_estimators=4), 5)
model_onnx = convert_sklearn(
model,
"gradient boosting classifier",
[("input", FloatTensorType([None, X.shape[1]]))],
dtype=np.float32,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingMultiClassClassifier",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #21
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_int(self):
model, X = fit_classification_model(
GradientBoostingClassifier(n_estimators=4), 5, is_int=True)
model_onnx = convert_sklearn(
model,
"gradient boosting classifier",
[("input", Int64TensorType([None, X.shape[1]]))],
dtype=np.float32,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingInt",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #22
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_bool(self):
model, X = fit_classification_model(
GradientBoostingClassifier(n_estimators=4), 5, is_bool=True)
model_onnx = convert_sklearn(
model,
"gradient boosting classifier",
[("input", BooleanTensorType([None, X.shape[1]]))],
dtype=np.float32,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingBool",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #23
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_multiclass_decision_function(self):
model, X = fit_classification_model(
GradientBoostingClassifier(n_estimators=4), 5)
options = {id(model): {'raw_scores': True}}
model_onnx = convert_sklearn(
model,
"gradient boosting classifier",
[("input", FloatTensorType([None, X.shape[1]]))],
dtype=np.float32,
options=options,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingMultiClassDecisionFunction",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
methods=['predict', 'decision_function'],
)
Example #24
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_multiclass_classification_init_zero(self):
model, X = fit_classification_model(
GradientBoostingClassifier(n_estimators=4, init='zero'), 4)
model_onnx = convert_sklearn(
model,
"gradient boosting classifier",
[("input", FloatTensorType([None, X.shape[1]]))],
dtype=np.float32,
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingMultiClassClassifierInitZero",
allow_failure="StrictVersion(onnxruntime.__version__)"
"<= StrictVersion('0.2.1')",
)
Example #25
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_regressor_lad_loss(self):
model, X = fit_regression_model(
GradientBoostingRegressor(n_estimators=3, loss="lad"))
model_onnx = convert_sklearn(
model,
"gradient boosting regression",
[("input", FloatTensorType([None, X.shape[1]]))],
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingRegressionLadLoss",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
)
Example #26
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_regressor_huber_loss(self):
model, X = fit_regression_model(
GradientBoostingRegressor(n_estimators=3, loss="huber"))
model_onnx = convert_sklearn(
model,
"gradient boosting regression",
[("input", FloatTensorType([None, X.shape[1]]))],
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingRegressionHuberLoss",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
)
Example #27
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_regressor_quantile_loss(self):
model, X = fit_regression_model(
GradientBoostingRegressor(n_estimators=3, loss="quantile"))
model_onnx = convert_sklearn(
model,
"gradient boosting regression",
[("input", FloatTensorType([None, X.shape[1]]))],
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingRegressionQuantileLoss",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
)
Example #28
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_regressor_int(self):
model, X = fit_regression_model(
GradientBoostingRegressor(random_state=42), is_int=True)
model_onnx = convert_sklearn(
model,
"gradient boosting regression",
[("input", Int64TensorType([None, X.shape[1]]))],
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingRegressionInt-Dec4",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
)
Example #29
| Source File: test_sklearn_gradient_boosting_converters.py From sklearn-onnx with MIT License | 6 votes |
|
def test_gradient_boosting_regressor_zero_init(self):
model, X = fit_regression_model(
GradientBoostingRegressor(n_estimators=30, init="zero",
random_state=42))
model_onnx = convert_sklearn(
model,
"gradient boosting regression",
[("input", FloatTensorType([None, X.shape[1]]))],
)
self.assertIsNotNone(model_onnx)
dump_data_and_model(
X,
model,
model_onnx,
basename="SklearnGradientBoostingRegressionZeroInit-Dec4",
allow_failure="StrictVersion(onnxruntime.__version__)"
" <= StrictVersion('0.2.1')"
)
Example #30
| Source File: test_CatBoost_converter.py From onnxmltools with MIT License | 6 votes |
|
def test_catboost_bin_classifier(self):
import onnxruntime
from distutils.version import StrictVersion
if StrictVersion(onnxruntime.__version__) >= StrictVersion('1.3.0'):
X, y = make_classification(n_samples=100, n_features=4, random_state=0)
catboost_model = catboost.CatBoostClassifier(task_type='CPU', loss_function='CrossEntropy',
n_estimators=10, verbose=0)
catboost_model.fit(X.astype(numpy.float32), y)
catboost_onnx = convert_catboost(catboost_model, name='CatBoostBinClassification',
doc_string='test binary classification')
self.assertTrue(catboost_onnx is not None)
dump_data_and_model(X.astype(numpy.float32), catboost_model, catboost_onnx, basename="CatBoostBinClass")
else:
warnings.warn('Converted CatBoost models for binary classification work with onnxruntime version 1.3.0 or '
'a newer one')
