saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-29 23:06:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/test/perftest
History
Dmitri Smirnov d1b1cdc5c4
Replace GSL with GSL-LITE submodule and fix up refs (#1920) 
Remove gsl subodule and replace with a local copy of gsl-lite
  Refactor for onnxruntime::make_unique
  gsl::span size and index are now size_t
  Remove lambda auto argument type detection.
  Remove constexpr from fail_fast in gsl due to Linux not being happy.
  Comment out std::stream support due to MacOS std lib broken.
  Move make_unique into include/core/common so it is accessible for server builds.
  Relax requirements for onnxruntime/test/providers/cpu/ml/write_scores_test.cc
  due to x86 build.
  Add ONNXRUNTIME_ROOT to Server Lib includes so gsl is recognized
2019-10-01 12:43:29 -07:00
..
posix Replace GSL with GSL-LITE submodule and fix up refs (#1920) 2019-10-01 12:43:29 -07:00
windows Replace GSL with GSL-LITE submodule and fix up refs (#1920) 2019-10-01 12:43:29 -07:00
command_args_parser.cc onnxruntime_perf_test: Add -y support to control parallel executor #threads (#1902) 2019-09-24 20:11:29 -07:00
command_args_parser.h Support large model(>2GB) (#520) 2019-03-05 21:27:12 -08:00
main.cc Ryanunderhill/api interface (#1855) 2019-09-20 13:39:11 -07:00
ort_test_session.cc Add C API for free dim override, fix missing API mention in InferenceTest.cs, fix confusing print statement in perf_test. (#1884) 2019-09-23 17:58:20 -07:00
ort_test_session.h Ryanunderhill/cxx api2 (#1091) 2019-05-24 11:15:51 -07:00
performance_runner.cc Replace GSL with GSL-LITE submodule and fix up refs (#1920) 2019-10-01 12:43:29 -07:00
performance_runner.h General performance testing tooling improvements (#1577) 2019-09-11 19:46:59 +10:00
README.md Implementation of Nuphar execution provider (#881) 2019-09-01 23:01:47 -07:00
ReadMe.txt
test_configuration.h Refine threading control options and move inter op thread pool to session state. (#1841) 2019-09-18 22:36:23 -07:00
test_session.h perf test runner: support NCHW->NHWC rotation (#976) 2019-05-07 11:50:29 -07:00
tf_test_session.h Fix a build break in tf_test_session.h (#1205) 2019-06-11 14:05:24 -07:00
TFModelInfo.cc Remove unneeded C APIs + some refactoring. (#1555) 2019-08-07 11:05:29 -07:00
TFModelInfo.h Integrate tensorflow into onnxruntime_perf_test tool 2019-04-09 15:55:08 -07:00
utils.h

README.md

ONNXRuntime Performance Test

onnxruntime_perf_test [options...] model_path result_file Options: -m [test_mode]: Specifies the test mode. Value coulde be 'duration' or 'times'. Provide 'duration' to run the test for a fix duration, and 'times' to repeated for a certain times. Default:'duration'. -e [cpu|cuda|mkldnn|tensorrt|ngraph|nuphar]: Specifies the provider 'cpu','cuda','mkldnn','tensorrt','ngraph' or 'nuphar'. Default:'cpu'. -r [repeated_times]: Specifies the repeated times if running in 'times' test mode.Default:1000. -t [seconds_to_run]: Specifies the seconds to run for 'duration' mode. Default:600. -p [profile_file]: Specifies the profile name to enable profiling and dump the profile data to the file. -s: Show statistics result, like P75, P90. -v: Show verbose information. -x: Use parallel executor, default (without -x): sequential executor. -h: help

Model path and input data dependency: Performance test uses the same input structure as onnx_test_runner. It requrires the directory trees as below:

--ModelName
    --test_data_set_0
        --input0.pb
    --test_data_set_2
        --input0.pb
    --model.onnx
The path of model.onnx needs to be provided as <model_path> argument.