Speech sample report output ambiguity (openvinotoolkit#15135)

* speech_sample: report output ambiguity Ticket 100574 * Add missing ;, ambogous->ambiguous * clang-format * Fix help message
iefode · Jan 23, 2023 · dcb3b20 · dcb3b20
1 parent bd1808c
commit dcb3b20
Show file tree

Hide file tree

Showing 4 changed files with 24 additions and 15 deletions.
diff --git a/samples/cpp/speech_sample/README.md b/samples/cpp/speech_sample/README.md
@@ -106,18 +106,19 @@ Options:
     -pc                        Optional. Enables per-layer performance report.
     -q "<mode>"                Optional. Input quantization mode: static (default), dynamic, or user (use with -sf).
     -qb "<integer>"            Optional. Weight bits for quantization: 8 or 16 (default)
-    -sf "<double>"             Optional. User-specified input scale factor for quantization (use with -q user). If the network contains multiple inputs, provide scale factors by separating them with commas.
-    -bs "<integer>"            Optional. Batch size 1-8
-    -layout "<string>"         Optional. Prompts how network layouts should be treated by application.For example, \"input1[NCHW],input2[NC]\" or \"[NCHW]\" in case of one input size.
+    -sf "<double>"             Optional. User-specified input scale factor for quantization (use with -q user). If the network contains multiple inputs, provide scale factors by separating them with commas. For example: <input_name1>:<sf1>,<input_name2>:<sf2> or just <sf> to be applied to all inputs
+    -bs "<integer>"            Optional. Batch size 1-8 (default 1)
     -r "<path>"                Optional. Read reference score file or named layers with corresponding score files and compare scores. Example of usage for single file: <reference.ark> or <reference.npz>. Example of usage for named layers: Example of usage for named layers: <layer1:port_num>=<reference_file2.ark>,<layer2:port_num>=<reference_file2.ark>.
     -rg "<path>"               Read GNA model from file using path/filename provided (required if -m is missing).
     -wg "<path>"               Optional. Write GNA model to file using path/filename provided.
     -we "<path>"               Optional. Write GNA embedded model to file using path/filename provided.
     -cw_l "<integer>"          Optional. Number of frames for left context windows (default is 0). Works only with context window networks. If you use the cw_l or cw_r flag, then batch size argument is ignored.
     -cw_r "<integer>"          Optional. Number of frames for right context windows (default is 0). Works only with context window networks. If you use the cw_r or cw_l flag, then batch size argument is ignored.
+    -layout "<string>"         Optional. Prompts how network layouts should be treated by application. For example, "input1[NCHW],input2[NC]" or "[NCHW]" in case of one input size.
     -pwl_me "<double>"         Optional. The maximum percent of error for PWL function.The value must be in <0, 100> range. The default value is 1.0.
     -exec_target "<string>"    Optional. Specify GNA execution target generation. May be one of GNA_TARGET_2_0, GNA_TARGET_3_0. By default, generation corresponds to the GNA HW available in the system or the latest fully supported generation by the software. See the GNA Plugin's GNA_EXEC_TARGET config option description.
     -compile_target "<string>" Optional. Specify GNA compile target generation. May be one of GNA_TARGET_2_0, GNA_TARGET_3_0. By default, generation corresponds to the GNA HW available in the system or the latest fully supported generation by the software. See the GNA Plugin's GNA_COMPILE_TARGET config option description.
+    -memory_reuse_off          Optional. Disables memory optimizations for compiled model.
 
 Available target devices:  CPU  GNA  GPU VPUX
 ```
@@ -132,9 +133,9 @@ mo --framework kaldi --input_model wsj_dnn5b.nnet --counts wsj_dnn5b.counts --re
 
 The following pre-trained models are available:
 
-- wsj_dnn5b_smbr
-- rm_lstm4f
 - rm_cnn4a_smbr
+- rm_lstm4f
+- wsj_dnn5b_smbr
 
 All of them can be downloaded from [https://storage.openvinotoolkit.org/models_contrib/speech/2021.2](https://storage.openvinotoolkit.org/models_contrib/speech/2021.2).
 

diff --git a/samples/cpp/speech_sample/main.cpp b/samples/cpp/speech_sample/main.cpp
@@ -343,14 +343,22 @@ int main(int argc, char* argv[]) {
             if (output_name_files.size() != outputs.size() && outputs.size()) {
                 throw std::logic_error("The number of output files is not equal to the number of network outputs.");
             }
-            count_file = output_name_files.empty() ? 1 : output_name_files.size();
+            count_file = output_name_files.size();
+            if (executableNet.outputs().size() > 1 && output_data.second.empty() && count_file == 1) {
+                throw std::logic_error("-o is ambiguous: the model has multiple outputs but only one file provided "
+                                       "without output name specification");
+            }
         }
         if (!reference_data.first.empty()) {
             reference_name_files = convert_str_to_vector(reference_data.first);
             if (reference_name_files.size() != outputs.size() && outputs.size()) {
                 throw std::logic_error("The number of reference files is not equal to the number of network outputs.");
             }
-            count_file = reference_name_files.empty() ? 1 : reference_name_files.size();
+            count_file = reference_name_files.size();
+            if (executableNet.outputs().size() > 1 && reference_data.second.empty() && count_file == 1) {
+                throw std::logic_error("-r is ambiguous: the model has multiple outputs but only one file provided "
+                                       "without output name specification");
+            }
         }
         if (count_file > executableNet.outputs().size()) {
             throw std::logic_error(

diff --git a/samples/cpp/speech_sample/speech_sample.hpp b/samples/cpp/speech_sample/speech_sample.hpp
@@ -62,14 +62,14 @@ static const char custom_cpu_library_message[] = "Required for CPU plugin custom
 /// @brief message for score output argument
 static const char output_message[] =
     "Optional. Output file name to save scores or Layer names with corresponding files names to save scores. Example "
-    "of usage for single file: <output.ark> or <output.npz>. Example of usage for named layers: Example of usage for "
-    "named layers: <layer1:port_num>=<output_file1.ark>,<layer2:port_num>=<output_file2.ark>.";
+    "of usage for single file: <output.ark> or <output.npz>. Example of usage for named layers: "
+    "<layer1:port_num>=<output_file1.ark>,<layer2:port_num>=<output_file2.ark>.";
 
 /// @brief message for reference score file argument
 static const char reference_score_message[] =
     "Optional. Read reference score file or named layers with corresponding score files and compare scores. Example of "
-    "usage for single file: <reference.ark> or <reference.npz>. Example of usage for named layers: Example of usage "
-    "for named layers: <layer1:port_num>=<reference_file2.ark>,<layer2:port_num>=<reference_file2.ark>.";
+    "usage for single file: <reference.ark> or <reference.npz>. Example of usage for named layers: "
+    "<layer1:port_num>=<reference_file2.ark>,<layer2:port_num>=<reference_file2.ark>.";
 
 /// @brief message for read GNA model argument
 static const char read_gna_model_message[] =
@@ -89,7 +89,7 @@ static const char write_embedded_model_generation_message[] =
 
 /// @brief message for quantization argument
 static const char quantization_message[] =
-    "Optional. Input quantization mode:  static (default), dynamic, or user (use with -sf).";
+    "Optional. Input quantization mode: static (default), dynamic, or user (use with -sf).";
 
 /// @brief message for quantization bits argument
 static const char quantization_bits_message[] = "Optional. Weight bits for quantization: 8 or 16 (default)";
@@ -222,7 +222,7 @@ static void show_usage() {
     std::cout << "    -pwl_me \"<double>\"         " << pwl_max_error_percent_message << std::endl;
     std::cout << "    -exec_target \"<string>\"    " << execution_target_message << std::endl;
     std::cout << "    -compile_target \"<string>\" " << compile_target_message << std::endl;
-    std::cout << "    -memory_reuse_off            " << memory_reuse_message << std::endl;
+    std::cout << "    -memory_reuse_off          " << memory_reuse_message << std::endl;
 }
 
 /**

diff --git a/samples/python/speech_sample/README.md b/samples/python/speech_sample/README.md
@@ -161,9 +161,9 @@ mo --framework kaldi --input_model wsj_dnn5b.nnet --counts wsj_dnn5b.counts --re
 
 The following pre-trained models are available:
 
-- wsj_dnn5b_smbr
-- rm_lstm4f
 - rm_cnn4a_smbr
+- rm_lstm4f
+- wsj_dnn5b_smbr
 
 All of them can be downloaded from [https://storage.openvinotoolkit.org/models_contrib/speech/2021.2](https://storage.openvinotoolkit.org/models_contrib/speech/2021.2).