module external.onnxruntime_perf_regression
¶
Short summary¶
module pymlbenchmark.external.onnxruntime_perf_regression
Implements a benchmark for a single regression about performance for onnxruntime.
Classes¶
class |
truncated documentation |
---|---|
Specific test to compare computing time predictions with scikit-learn and onnxruntime for a binary … |
Methods¶
method |
truncated documentation |
---|---|
Returns a random datasets. |
|
Returns a few functions, tests methods perdict, predict_proba for both scikit-learn and OnnxInference … |
Documentation¶
Implements a benchmark for a single regression about performance for onnxruntime.
- class pymlbenchmark.external.onnxruntime_perf_regression.OnnxRuntimeBenchPerfTestRegression(estimator, dim=None, N_fit=100000, runtimes=('python_compiled', 'onnxruntime1'), onnx_options=None, dtype=<class 'numpy.float32'>, **opts)¶
Bases:
OnnxRuntimeBenchPerfTest
Specific test to compare computing time predictions with scikit-learn and onnxruntime for a binary classification. See example l-example-onnxruntime-linreg. The class requires the following modules to be installed: onnx, onnxruntime, skl2onnx, mlprodict.
- Parameters:
estimator – estimator class
dim – number of features
N_fit – number of observations to fit an estimator
runtimes – runtimes to test for class OnnxInference
opts – training settings
onnx_options – ONNX conversion options
dtype – dtype (float32 or float64)
- _get_random_dataset(N, dim)¶
Returns a random datasets.
- fcts(dim=None, **kwargs)¶
Returns a few functions, tests methods perdict, predict_proba for both scikit-learn and OnnxInference multiplied by the number of runtime to test.