IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[BENCHMARK_APP] Help message cleanup (#14786)

Browse Source
This commit is contained in:
Tomasz Dołbniak 2023-01-05 14:21:09 +01:00 committed by GitHub
parent 99c7ee1c18
commit 13d01d969b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 80 additions and 78 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
samples/cpp/benchmark_app/README.md
View File

@ -113,43 +113,43 @@ Running the application with the `-h` or `--help` option yields the following us
benchmark_app [OPTION] benchmark_app [OPTION]
Options: Options:
-h, --help Print a usage message -h, --help Print the usage message
-m "<path>" Required. Path to an .xml/.onnx file with a trained model or to a .blob files with a trained compiled model. -m <path> Required. Path to an .xml/.onnx file with a trained model or to a .blob files with a trained compiled model.
-i "<path>" Optional. Path to a folder with images and/or binaries or to specific image or binary file. -i <path> Optional. Path to a folder with images and/or binaries or to specific image or binary file.
In case of dynamic shapes models with several inputs provide the same number of files for each input (except cases with single file for any input):"input1:1.jpg input2:1.bin", "input1:1.bin,2.bin input2:3.bin input3:4.bin,5.bin ". Also you can pass specific keys for inputs: "random" - for fillling input with random data, "image_info" - for filling input with image size. In case of dynamic shapes models with several inputs provide the same number of files for each input (except cases with single file for any input):"input1:1.jpg input2:1.bin", "input1:1.bin,2.bin input2:3.bin input3:4.bin,5.bin ". Also you can pass specific keys for inputs: "random" - for fillling input with random data, "image_info" - for filling input with image size.
You should specify either one files set to be used for all inputs (without providing input names) or separate files sets for every input of model (providing inputs names). You should specify either one files set to be used for all inputs (without providing input names) or separate files sets for every input of model (providing inputs names).
-d "<device>" Optional. Specify a target device to infer on (the list of available devices is shown below). Default value is CPU. Use "-d HETERO:<comma-separated_devices_list>" format to specify HETERO plugin. Use "-d MULTI:<comma-separated_devices_list>" format to specify MULTI plugin. The application looks for a suitable plugin for the specified device. -d <device> Optional. Specify a target device to infer on (the list of available devices is shown below). Default value is CPU. Use "-d HETERO:<comma-separated_devices_list>" format to specify HETERO plugin. Use "-d MULTI:<comma-separated_devices_list>" format to specify MULTI plugin. The application looks for a suitable plugin for the specified device.
-extensions "<absolute_path>" Required for custom layers (extensions). Absolute path to a shared library with the kernels implementations. -extensions <absolute_path> Required for custom layers (extensions). Absolute path to a shared library with the kernels implementations.
-c "<absolute_path>" Required for GPU custom kernels. Absolute path to an .xml file with the kernels description. -c <absolute_path> Required for GPU custom kernels. Absolute path to an .xml file with the kernels description.
-hint "performance hint (latency or throughput or cumulative_throughput or none)" Optional. Performance hint allows the OpenVINO device to select the right model-specific settings. -hint <performance hint> (latency or throughput or cumulative_throughput or none) Optional. Performance hint allows the OpenVINO device to select the right model-specific settings.
'throughput' or 'tput': device performance mode will be set to THROUGHPUT. 'throughput' or 'tput': device performance mode will be set to THROUGHPUT.
'cumulative_throughput' or 'ctput': device performance mode will be set to CUMULATIVE_THROUGHPUT. 'cumulative_throughput' or 'ctput': device performance mode will be set to CUMULATIVE_THROUGHPUT.
'latency': device performance mode will be set to LATENCY. 'latency': device performance mode will be set to LATENCY.
'none': no device performance mode will be set. 'none': no device performance mode will be set.
Using explicit 'nstreams' or other device-specific options, please set hint to 'none' Using explicit 'nstreams' or other device-specific options, please set hint to 'none'
-api "<sync/async>" Optional (deprecated). Enable Sync/Async API. Default value is "async". -api <sync/async> Optional (deprecated). Enable Sync/Async API. Default value is "async".
-niter "<integer>" Optional. Number of iterations. If not specified, the number of iterations is calculated depending on a device. -niter <integer> Optional. Number of iterations. If not specified, the number of iterations is calculated depending on a device.
-nireq "<integer>" Optional. Number of infer requests. Default value is determined automatically for device. -nireq <integer> Optional. Number of infer requests. Default value is determined automatically for device.
-b "<integer>" Optional. Batch size value. If not specified, the batch size value is determined from Intermediate Representation. -b <integer> Optional. Batch size value. If not specified, the batch size value is determined from Intermediate Representation.
-t Optional. Time in seconds to execute topology. -t Optional. Time in seconds to execute topology.
-shape Optional. Set shape for model input. For example, "input1[1,3,224,224],input2[1,4]" or "[1,3,224,224]" in case of one input size. This parameter affect model input shape and can be dynamic. For dynamic dimensions use symbol `?` or '-1'. Ex. [?,3,?,?]. For bounded dimensions specify range 'min..max'. Ex. [1..10,3,?,?]. -shape Optional. Set shape for model input. For example, "input1[1,3,224,224],input2[1,4]" or "[1,3,224,224]" in case of one input size. This parameter affect model input shape and can be dynamic. For dynamic dimensions use symbol `?` or '-1'. Ex. [?,3,?,?]. For bounded dimensions specify range 'min..max'. Ex. [1..10,3,?,?].
-data_shape Required for models with dynamic shapes. Set shape for input blobs. In case of one input size: "[1,3,224,224]" or "input1[1,3,224,224],input2[1,4]". In case of several input sizes provide the same number for each input (except cases with single shape for any input): "[1,3,128,128][3,3,128,128][1,3,320,320]", "input1[1,1,128,128][1,1,256,256],input2[80,1]" or "input1[1,192][1,384],input2[1,192][1,384],input3[1,192][1,384],input4[1,192][1,384]". If model shapes are all static specifying the option will cause an exception. -data_shape Required for models with dynamic shapes. Set shape for input blobs. In case of one input size: "[1,3,224,224]" or "input1[1,3,224,224],input2[1,4]". In case of several input sizes provide the same number for each input (except cases with single shape for any input): "[1,3,128,128][3,3,128,128][1,3,320,320]", "input1[1,1,128,128][1,1,256,256],input2[80,1]" or "input1[1,192][1,384],input2[1,192][1,384],input3[1,192][1,384],input4[1,192][1,384]". If model shapes are all static specifying the option will cause an exception.
-layout Optional. Prompts how model layouts should be treated by application. For example, "input1[NCHW],input2[NC]" or "[NCHW]" in case of one input size. -layout Optional. Prompts how model layouts should be treated by application. For example, "input1[NCHW],input2[NC]" or "[NCHW]" in case of one input size.
-cache_dir "<path>" Optional. Enables caching of loaded models to specified directory. List of devices which support caching is shown at the end of this message. -cache_dir <path> Optional. Enables caching of loaded models to specified directory. List of devices which support caching is shown at the end of this message.
-load_from_file Optional. Loads model from file directly without read_model. All CNNNetwork options (like re-shape) will be ignored -load_from_file Optional. Loads model from file directly without read_model. All CNNNetwork options (like re-shape) will be ignored
-latency_percentile Optional. Defines the percentile to be reported in latency metric. The valid range is [1, 100]. The default value is 50 (median). -latency_percentile Optional. Defines the percentile to be reported in latency metric. The valid range is [1, 100]. The default value is 50 (median).
device-specific performance options: device-specific performance options:
-nstreams "<integer>" Optional. Number of streams to use for inference on the CPU, GPU or MYRIAD devices (for HETERO and MULTI device cases use format <dev1>:<nstreams1>,<dev2>:<nstreams2> or just <nstreams>). Default value is determined automatically for a device.Please note that although the automatic selection usually provides a reasonable performance, it still may be non - optimal for some cases, especially for very small models. See sample's README for more details. Also, using nstreams>1 is inherently throughput-oriented option, while for the best-latency estimations the number of streams should be set to 1. -nstreams <integer> Optional. Number of streams to use for inference on the CPU, GPU or MYRIAD devices (for HETERO and MULTI device cases use format <dev1>:<nstreams1>,<dev2>:<nstreams2> or just <nstreams>). Default value is determined automatically for a device.Please note that although the automatic selection usually provides a reasonable performance, it still may be non - optimal for some cases, especially for very small models. See sample's README for more details. Also, using nstreams>1 is inherently throughput-oriented option, while for the best-latency estimations the number of streams should be set to 1.
-nthreads "<integer>" Optional. Number of threads to use for inference on the CPU (including HETERO and MULTI cases). -nthreads <integer> Optional. Number of threads to use for inference on the CPU (including HETERO and MULTI cases).
-pin ("YES"|"CORE")/"HYBRID_AWARE"/("NO"|"NONE")/"NUMA" Optional. Explicit inference threads binding options (leave empty to let the OpenVINO to make a choice): -pin <string> ("YES"|"CORE") / "HYBRID_AWARE" / ("NO"|"NONE") / "NUMA" Optional. Explicit inference threads binding options (leave empty to let the OpenVINO make a choice):
enabling threads->cores pinning("YES", which is already default for any conventional CPU), enabling threads->cores pinning("YES", which is already default for any conventional CPU),
letting the runtime to decide on the threads->different core types("HYBRID_AWARE", which is default on the hybrid CPUs) letting the runtime to decide on the threads->different core types("HYBRID_AWARE", which is default on the hybrid CPUs)
threads->(NUMA)nodes("NUMA") or threads->(NUMA)nodes("NUMA") or
completely disable("NO") CPU inference threads pinning completely disable("NO") CPU inference threads pinning
Statistics dumping options: Statistics dumping options:
-report_type "<type>" Optional. Enable collecting statistics report. "no_counters" report contains configuration options specified, resulting FPS and latency. "average_counters" report extends "no_counters" report and additionally includes average PM counters values for each layer from the model. "detailed_counters" report extends "average_counters" report and additionally includes per-layer PM counters and latency for each executed infer request. -report_type <type> Optional. Enable collecting statistics report. "no_counters" report contains configuration options specified, resulting FPS and latency. "average_counters" report extends "no_counters" report and additionally includes average PM counters values for each layer from the model. "detailed_counters" report extends "average_counters" report and additionally includes per-layer PM counters and latency for each executed infer request.
-report_folder Optional. Path to a folder where statistics report is stored. -report_folder Optional. Path to a folder where statistics report is stored.
-json_stats Optional. Enables JSON-based statistics output (by default reporting system will use CSV format). Should be used together with -report_folder option. -json_stats Optional. Enables JSON-based statistics output (by default reporting system will use CSV format). Should be used together with -report_folder option.
-exec_graph_path Optional. Path to a file where to store executable graph information serialized. -exec_graph_path Optional. Path to a file where to store executable graph information serialized.
@ -180,10 +180,10 @@ Options:
} }
} }
-infer_precision "<element type>"Optional. Inference precision -infer_precision Optional. Specifies the inference precision. Example #1: '-infer_precision bf16'. Example #2: '-infer_precision CPU:bf16,GPU:f32'
-ip <value> Optional. Specifies precision for all input layers of the model. -ip <value> Optional. Specifies precision for all input layers of the model.
-op <value> Optional. Specifies precision for all output layers of the model. -op <value> Optional. Specifies precision for all output layers of the model.
-iop "<value>" Optional. Specifies precision for input and output layers by name. -iop <value> Optional. Specifies precision for input and output layers by name.
Example: -iop "input:FP16, output:FP16". Example: -iop "input:FP16, output:FP16".
Notice that quotes are required. Notice that quotes are required.
Overwrites precision from ip and op options for specified layers. Overwrites precision from ip and op options for specified layers.

42
samples/cpp/benchmark_app/benchmark_app.hpp
View File

@ -24,7 +24,7 @@
#endif #endif
/// @brief message for help argument /// @brief message for help argument
static const char help_message[] = "Print a usage message"; static const char help_message[] = "Print the usage message";
/// @brief message for images argument /// @brief message for images argument
static const char input_message[] = static const char input_message[] =
@ -121,7 +121,7 @@ static const char batch_size_message[] =
// @brief message for CPU threads pinning option // @brief message for CPU threads pinning option
static const char infer_threads_pinning_message[] = static const char infer_threads_pinning_message[] =
"Optional. Explicit inference threads binding options (leave empty to let the OpenVINO to make a choice):\n" "Optional. Explicit inference threads binding options (leave empty to let the OpenVINO make a choice):\n"
"\t\t\t\tenabling threads->cores pinning(\"YES\", which is already default for any conventional CPU), \n" "\t\t\t\tenabling threads->cores pinning(\"YES\", which is already default for any conventional CPU), \n"
"\t\t\t\tletting the runtime to decide on the threads->different core types(\"HYBRID_AWARE\", which is default on " "\t\t\t\tletting the runtime to decide on the threads->different core types(\"HYBRID_AWARE\", which is default on "
"the hybrid CPUs) \n" "the hybrid CPUs) \n"
@ -226,7 +226,9 @@ static const char load_from_file_message[] = "Optional. Loads model from file di
" All CNNNetwork options (like re-shape) will be ignored"; " All CNNNetwork options (like re-shape) will be ignored";
// @brief message for inference_precision // @brief message for inference_precision
static const char inference_precision_message[] = "Optional. Inference precision"; static const char inference_precision_message[] =
"Optional. Specifies the inference precision. Example #1: '-infer_precision bf16'. Example #2: '-infer_precision "
"CPU:bf16,GPU:f32'";
static constexpr char inputs_precision_message[] = "Optional. Specifies precision for all input layers of the model."; static constexpr char inputs_precision_message[] = "Optional. Specifies precision for all input layers of the model.";
@ -403,34 +405,34 @@ static void show_usage() {
std::cout << "Options:" << std::endl; std::cout << "Options:" << std::endl;
std::cout << std::endl; std::cout << std::endl;
std::cout << " -h, --help " << help_message << std::endl; std::cout << " -h, --help " << help_message << std::endl;
std::cout << " -m \"<path>\" " << model_message << std::endl; std::cout << " -m <path> " << model_message << std::endl;
std::cout << " -i \"<path>\" " << input_message << std::endl; std::cout << " -i <path> " << input_message << std::endl;
std::cout << " -d \"<device>\" " << target_device_message << std::endl; std::cout << " -d <device> " << target_device_message << std::endl;
std::cout << " -extensions \"<absolute_path>\" " << custom_extensions_library_message << std::endl; std::cout << " -extensions <absolute_path> " << custom_extensions_library_message << std::endl;
std::cout << " -c \"<absolute_path>\" " << custom_cldnn_message << std::endl; std::cout << " -c <absolute_path> " << custom_cldnn_message << std::endl;
std::cout << " -hint \"performance hint (latency or throughput or cumulative_throughput or none)\" " std::cout << " -hint <performance hint> (latency or throughput or cumulative_throughput or none) "
<< hint_message << std::endl; << hint_message << std::endl;
std::cout << " -api \"<sync/async>\" " << api_message << std::endl; std::cout << " -api <sync/async> " << api_message << std::endl;
std::cout << " -niter \"<integer>\" " << iterations_count_message << std::endl; std::cout << " -niter <integer> " << iterations_count_message << std::endl;
std::cout << " -nireq \"<integer>\" " << infer_requests_count_message << std::endl; std::cout << " -nireq <integer> " << infer_requests_count_message << std::endl;
std::cout << " -b \"<integer>\" " << batch_size_message << std::endl; std::cout << " -b <integer> " << batch_size_message << std::endl;
std::cout << " -t " << execution_time_message << std::endl; std::cout << " -t " << execution_time_message << std::endl;
std::cout << " -shape " << shape_message << std::endl; std::cout << " -shape " << shape_message << std::endl;
std::cout << " -data_shape " << data_shape_message << std::endl; std::cout << " -data_shape " << data_shape_message << std::endl;
std::cout << " -layout " << layout_message << std::endl; std::cout << " -layout " << layout_message << std::endl;
std::cout << " -cache_dir \"<path>\" " << cache_dir_message << std::endl; std::cout << " -cache_dir <path> " << cache_dir_message << std::endl;
std::cout << " -load_from_file " << load_from_file_message << std::endl; std::cout << " -load_from_file " << load_from_file_message << std::endl;
std::cout << " -latency_percentile " << infer_latency_percentile_message << std::endl; std::cout << " -latency_percentile " << infer_latency_percentile_message << std::endl;
std::cout << std::endl << " device-specific performance options:" << std::endl; std::cout << std::endl << " device-specific performance options:" << std::endl;
std::cout << " -nstreams \"<integer>\" " << infer_num_streams_message << std::endl; std::cout << " -nstreams <integer> " << infer_num_streams_message << std::endl;
std::cout << " -nthreads \"<integer>\" " << infer_num_threads_message << std::endl; std::cout << " -nthreads <integer> " << infer_num_threads_message << std::endl;
std::cout << " -pin (\"YES\"|\"CORE\")/\"HYBRID_AWARE\"/(\"NO\"|\"NONE\")/\"NUMA\" " std::cout << " -pin <string> (\"YES\"|\"CORE\") / \"HYBRID_AWARE\" / (\"NO\"|\"NONE\") / \"NUMA\" "
<< infer_threads_pinning_message << std::endl; << infer_threads_pinning_message << std::endl;
#ifdef HAVE_DEVICE_MEM_SUPPORT #ifdef HAVE_DEVICE_MEM_SUPPORT
std::cout << " -use_device_mem " << use_device_mem_message << std::endl; std::cout << " -use_device_mem " << use_device_mem_message << std::endl;
#endif #endif
std::cout << std::endl << " Statistics dumping options:" << std::endl; std::cout << std::endl << " Statistics dumping options:" << std::endl;
std::cout << " -report_type \"<type>\" " << report_type_message << std::endl; std::cout << " -report_type <type> " << report_type_message << std::endl;
std::cout << " -report_folder " << report_folder_message << std::endl; std::cout << " -report_folder " << report_folder_message << std::endl;
std::cout << " -json_stats " << json_stats_message << std::endl; std::cout << " -json_stats " << json_stats_message << std::endl;
std::cout << " -exec_graph_path " << exec_graph_path_message << std::endl; std::cout << " -exec_graph_path " << exec_graph_path_message << std::endl;
@ -439,10 +441,10 @@ static void show_usage() {
std::cout << " -pcseq " << pcseq_message << std::endl; std::cout << " -pcseq " << pcseq_message << std::endl;
std::cout << " -dump_config " << dump_config_message << std::endl; std::cout << " -dump_config " << dump_config_message << std::endl;
std::cout << " -load_config " << load_config_message << std::endl; std::cout << " -load_config " << load_config_message << std::endl;
std::cout << " -infer_precision \"<element type>\"" << inference_precision_message << std::endl; std::cout << " -infer_precision " << inference_precision_message << std::endl;
std::cout << " -ip <value> " << inputs_precision_message << std::endl; std::cout << " -ip <value> " << inputs_precision_message << std::endl;
std::cout << " -op <value> " << outputs_precision_message << std::endl; std::cout << " -op <value> " << outputs_precision_message << std::endl;
std::cout << " -iop \"<value>\" " << iop_message << std::endl; std::cout << " -iop <value> " << iop_message << std::endl;
std::cout << " -mean_values [R,G,B] " << mean_values_message << std::endl; std::cout << " -mean_values [R,G,B] " << mean_values_message << std::endl;
std::cout << " -scale_values [R,G,B] " << scale_values_message << std::endl; std::cout << " -scale_values [R,G,B] " << scale_values_message << std::endl;
std::cout << " -inference_only " << inference_only_message << std::endl; std::cout << " -inference_only " << inference_only_message << std::endl;

2
tools/benchmark_tool/openvino/tools/benchmark/parameters.py
View File

@ -161,7 +161,7 @@ def parse_args():
" }\n" " }\n"
" }\n") " }\n")
args.add_argument('-infer_precision', type=str, required=False, args.add_argument('-infer_precision', type=str, required=False,
help='Optional. Hint to specifies inference precision. Example: -infer_precision CPU:bf16,GPU:f32') help='Optional. Specifies the inference precision. Example #1: \'-infer_precision bf16\'. Example #2: \'-infer_precision CPU:bf16,GPU:f32\'')
args.add_argument('-ip', '--input_precision', type=str, required=False, choices=['u8', 'U8', 'f16','FP16', 'f32','FP32'], args.add_argument('-ip', '--input_precision', type=str, required=False, choices=['u8', 'U8', 'f16','FP16', 'f32','FP32'],
help='Optional. Specifies precision for all input layers of the model.') help='Optional. Specifies precision for all input layers of the model.')
args.add_argument('-op', '--output_precision', type=str, required=False, choices=['u8', 'U8', 'f16','FP16', 'f32','FP32'], args.add_argument('-op', '--output_precision', type=str, required=False, choices=['u8', 'U8', 'f16','FP16', 'f32','FP32'],