ONNX benchmarks¶
The following benchmarks compare runtime or backend with ONNX.
onxruntime VS scikit-learn¶
The following benchmark measures the prediction time between scikit-learn and onnxruntime for different models related to one-off predictions and batch predictions. onnxruntime allows for some models to run batch predictions by using broadcasting. It is not available for all models.
- Prediction time scikit-learn / onnxruntime: summary
- Prediction time scikit-learn / onnxruntime for LogisticRegression
- Prediction time scikit-learn / onnxruntime for DecisionTreeClassifier
- Prediction time scikit-learn / onnxruntime for KNeighborsClassifier
- Prediction time scikit-learn / onnxruntime for RandomForestClassifier
- Prediction time scikit-learn / onnxruntime for MLPClassifier
onnxruntime specific configurations¶
The following benchmark look into simplified models to help understand how onnxruntime works.
ONNX versus other implementations¶
The following benchmarks were implemented in other repositories. The first one looks into the implementation of a logistic regression with python, C++ or C++ optimization provided by other libraries.
