Methods

Summary

method class parent truncated documentation
__init__ BenchPerf  
__init__ BenchPerfTest  
__init__ OnnxRuntimeBenchPerfTestBinaryClassification  
_init OnnxRuntimeBenchPerfTestBinaryClassification Finalizes the init.
data BenchPerfTest Generates one testing dataset.
data OnnxRuntimeBenchPerfTestBinaryClassification Generates random features.
dump_error BenchPerfTest Dumps everything which is needed to investigate an error. Everything is pickled in the current folder or dump_folder
enumerate_run_benchs BenchPerf Runs the benchmark.
enumerate_tests BenchPerf Enumerates all possible options.
extract_model_info_ort OnnxRuntimeBenchPerfTestBinaryClassification Populates member self.ort_info with additional information on the ONNX graph.
extract_model_info_skl OnnxRuntimeBenchPerfTestBinaryClassification Populates member self.skl_info with additional information on the model such as the number of node for …
fct_filter_test BenchPerf Tells if the test by conf is valid or not.
fcts BenchPerfTest Returns the function call to test, it produces a dictionary {name: fct} where name is the name of …
fcts OnnxRuntimeBenchPerfTestBinaryClassification Returns four functions, tests methods perdict, predict_proba for both scikit-learn and onnxruntime. …
model_info OnnxRuntimeBenchPerfTestBinaryClassification Returns additional informations about a model.
validate BenchPerfTest Runs validations after the test was done to make sure it was valid.
validate OnnxRuntimeBenchPerfTestBinaryClassification Checks that methods predict and predict_proba returns the same results for both scikit-learn and …