Specific Benchmarks

The code is specifically implemented to test the same scenario on multiple models or configuration.

onnxruntime

pymlbenchmark.external.OnnxRuntimeBenchPerfTestBinaryClassification (self, classifier, dim = None, opts)

Specific test to compare computing time predictions with scikit-learn and onnxruntime. See example Benchmark of onnxruntime on LogisticRegression. The class requires the following modules to be installed: onnx, onnxruntime, skl2onnx.

pymlbenchmark.external.onnxruntime_perf_binary_classifiers ()

Returns a list of benchmarks for binary classifier. It compares onnxruntime predictions against scikit-learn.

pymlbenchmark.external.run_onnxruntime_test (folder, name, repeat = 100, verbose = True, stop_if_error = True, validate = True, fLOG = None)

Runs a benchmark for onnxruntime.