GstInference/Benchmarks: Difference between revisions

From RidgeRun Developer Wiki
Line 164: Line 164:
   </style>
   </style>
    
    
   <button class="button" id="addData">Show CPU </button>
   <button class="button" id="show_inceptionv1">Show InceptionV1 </button>
   <button class="button" id="showFPS">Show FPS </button>
   <button class="button" id="show_inceptionv2">Show InceptionV2 </button>
   <button class="button" id="reset">Show All</button>
   <button class="button" id="show_inceptionv3">Show InceptionV3 </button>
   Show InceptionV1: <input class="button" type="checkbox" id="myCheck" checked=true>
   <button class="button" id="show_inceptionv4">Show InceptionV4 </button>
  Show InceptionV2: <input  class="button" type="checkbox" id="myCheck2" checked=true>


<br><br>
<br><br>
<div id="chart_div" style="width: 800px; height: 500px;"></div>
<div id="chart_div" style="width: 800px; height: 500px;"></div>
<br><br>
<button class="button" id="show_tensorflow">Show Tensorflow </button>
<button class="button" id="show_tflite">Show Tensorflow-Lite </button>
<div id="chart_div1" style="width: 800px; height: 500px;"></div>
<br><br>
<button class="button" id="show_x86">Show x86 </button>
<button class="button" id="show_x86_gpu">Show X86+GPU </button>
<button class="button" id="show_tx2">Show Tx2 </button>
<button class="button" id="show_tx2_gpu">Show TX2+GPU </button>
<button class="button" id="show_coral">Show Coral </button>
<button class="button" id="show_coral_tpu">Show Coral+TPU </button>
<div id="chart_div2" style="width: 800px; height: 500px;"></div>


<script>
<script>
Line 179: Line 190:
       function drawStuff() {
       function drawStuff() {


        var check_box2 = document.getElementById("myCheck2");
 
          check_box2.onchange = show_1;
 
          var check_box = document.getElementById("myCheck");
          check_box.onchange = show_0;
         var chartDiv = document.getElementById('chart_div');
         var chartDiv = document.getElementById('chart_div');
        var chartDiv1 = document.getElementById('chart_div1');
        var chartDiv2 = document.getElementById('chart_div2');


         var data = google.visualization.arrayToDataTable([
         var table_backend_platform = google.visualization.arrayToDataTable([
           ['Model', 'x86-FPS', 'Xavier-FPS', 'x64-CPU', 'Xavier-CPU'],
          ['Platform',
           ['InceptionV1', 20.164, 7.642, 48, 71],
          'InceptionV1 \n Tensorflow',
           ['InceptionV2', 14.821, 5.587, 44, 68],
          'InceptionV1 \n Tensorflow-Lite',
           ['InceptionV3', 6.086,  2.286, 50, 72],
          'InceptionV2 \n Tensorflow',
           ['InceptionV4', 2.977,  1.153, 50, 72],
          'InceptionV2 \n Tensorflow-Lite',
           ['TinyyoloV2',  9.111, 2.966, 47, 67],
          'InceptionV3 \n Tensorflow',
           ['TinyyoloV3',  10.286, 3.43, 45, 63]
          'InceptionV3 \n Tensorflow-Lite',
          'InceptionV4 \n Tensorflow',
          'InceptionV4 \n Tensorflow-Lite'],
          ['x86',      20.164, 19.545, 18.164, 17.642, 16.164, 15.642, 14.164, 13.642],
          ['x86+GPU',  25.821, 24.587, 23.164, 22.642, 21.164, 20.642, 19.164, 18.642],
          ['TX2',      24.821, 23.587, 22.164, 21.642, 20.164, 19.642, 18.164, 17.642],
          ['TX2-GPU',  27.821, 26.587, 25.164, 24.642, 23.164, 22.642, 21.164, 20.642],
          ['Coral',    16.111, 15.966, 14.164, 13.642, 12.164, 11.642, 10.164, 9.642],
          ['Coral+TPU', 18.111, 17.966, 16.164, 15.642, 14.164, 13.642, 12.164, 11.642]
        ]);
        var table_model_platform = google.visualization.arrayToDataTable([
           ['Model',
          'Tensorflow \n x86',
          'Tensorflow \n x86+GPU',
          'Tensorflow \n TX2',
          'Tensorflow \n TX2+GPU',
          'Tensorflow \n Coral',
          'Tensorflow \n Coral+TPU',
          'Tensorflow-Lite \n x86',
          'Tensorflow-Lite \n x86+GPU',
          'Tensorflow-Lite \n TX2',
          'Tensorflow-Lite \n TX2+GPU',
          'Tensorflow-Lite \n Coral',
          'Tensorflow-Lite \n Coral+TPU'],
           ['InceptionV1',   20.164, 25.642, 24.164, 27.642, 16.164, 18.642, 19.164, 24.642, 23.164, 26.642, 15.164, 17.642],
           ['InceptionV2',   18.821, 23.587, 22.164, 25.642, 14.164, 16.642, 17.164, 22.642, 21.164, 24.642, 13.164, 15.642],
           ['InceptionV3',   16.086,  21.286, 20.164, 23.642, 12.164, 14.642, 15.164, 20.642, 19.164, 22.642, 11.164, 13.642],
           ['InceptionV4',   14.977,  19.153, 18.164, 21.642, 10.164, 12.642, 13.164, 18.642, 17.164, 20.642, 9.164, 11.642]
        ]);
        var table_model_backend = google.visualization.arrayToDataTable([
        ['Model',
          'Tensorflow \n x86',
          'Tensorflow \n x86+GPU',
          'Tensorflow \n TX2',
          'Tensorflow \n TX2+GPU',
          'Tensorflow \n Coral',
          'Tensorflow \n Coral+TPU',
          'Tensorflow-Lite \n x86',
          'Tensorflow-Lite \n x86+GPU',
          'Tensorflow-Lite \n TX2',
          'Tensorflow-Lite \n TX2+GPU',
          'Tensorflow-Lite \n Coral',
          'Tensorflow-Lite \n Coral+TPU'],
          ['InceptionV1',  20.164, 25.642, 24.164, 27.642, 16.164, 18.642, 19.164, 24.642, 23.164, 26.642, 15.164, 17.642],
          ['InceptionV2',  18.821, 23.587, 22.164, 25.642, 14.164, 16.642, 17.164, 22.642, 21.164, 24.642, 13.164, 15.642],
           ['InceptionV3',  16.086,  21.286, 20.164, 23.642, 12.164, 14.642, 15.164, 20.642, 19.164, 22.642, 11.164, 13.642],
           ['InceptionV4',  14.977,  19.153, 18.164, 21.642, 10.164, 12.642, 13.164, 18.642, 17.164, 20.642, 9.164, 11.642]
         ]);
         ]);


Line 198: Line 255:
           width: 900,
           width: 900,
           chart: {
           chart: {
             title: 'Model performance',
            title: 'Backend Vs Platform per model',
          },
          series: {
            0: { axis: 'distance' }, // Bind series 0 to an axis named 'distance'.
          },
          axes: {
            y: {
              distance: {side: 'left',label: 'FPS'}, // Left y-axis.
            }
          }
        };
        var materialOptions1 = {
          width: 900,
          chart: {
             title: 'Model Vs Platform per backend',
          },
          series: {
            0: { axis: 'distance' }, // Bind series 0 to an axis named 'distance'.
          },
          axes: {
            y: {
              distance: {side: 'left',label: 'FPS'}, // Left y-axis.
            }
          }
        };
        var materialOptions2 = {
          width: 900,
          chart: {
            title: 'Model Vs Backend per Platform',
           },
           },
           series: {
           series: {
             0: { axis: 'distance' }, // Bind series 0 to an axis named 'distance'.
             0: { axis: 'distance' }, // Bind series 0 to an axis named 'distance'.
            //1: { axis: 'brightness' } // Bind series 1 to an axis named 'brightness'.
           },
           },
           axes: {
           axes: {
             y: {
             y: {
               distance: {side: 'left',label: 'FPS'}, // Left y-axis.
               distance: {side: 'left',label: 'FPS'}, // Left y-axis.
              brightness: {side: 'right', label: 'CPU usage'} // Right y-axis.
             }
             }
           }
           }
         };
         };
         var materialChart = new google.charts.Bar(chartDiv);
         var materialChart = new google.charts.Bar(chartDiv);
         view = new google.visualization.DataView(data);
        var materialChart1 = new google.charts.Bar(chartDiv1);
        var materialChart2 = new google.charts.Bar(chartDiv2);
         view = new google.visualization.DataView(table_backend_platform);
        view1 = new google.visualization.DataView(table_model_platform);
        view2 = new google.visualization.DataView(table_model_backend);
 
         function drawMaterialChart() {
         function drawMaterialChart() {
           var materialChart = new google.charts.Bar(chartDiv);
           var materialChart = new google.charts.Bar(chartDiv);
           materialChart.draw(data, google.charts.Bar.convertOptions(materialOptions));
          var materialChart1 = new google.charts.Bar(chartDiv1);
           view = new google.visualization.DataView(data);
          var materialChart2 = new google.charts.Bar(chartDiv2);
           materialChart.draw(table_backend_platform, google.charts.Bar.convertOptions(materialOptions));
           materialChart1.draw(table_model_platform, google.charts.Bar.convertOptions(materialOptions1));
          materialChart2.draw(table_model_backend, google.charts.Bar.convertOptions(materialOptions2));
          init_charts();
        }
        function init_charts(){
          view.setColumns([0,1,2]);
          view.hideColumns([3,4,5,6,7,8]);
          materialChart.draw(view, materialOptions);
          view1.setColumns([0,1,2,3,4,5,6]);
          view1.hideColumns([7,8,9,10,11,12]);
          materialChart1.draw(view1, materialOptions1);
          view2.setColumns([0,1,7]);
          view2.hideColumns([2,3,4,5,6,8,9,10,11,12]);
          materialChart2.draw(view2, materialOptions2);
 
        }


          //button.onclick = addNewRow;


        /*Select the backend to filter the data to show in the chart*/
        var show_inceptionv1 = document.getElementById('show_inceptionv1');
        show_inceptionv1.onclick = function () {
          view.setColumns([0,1,2]);
          view.hideColumns([3,4,5,6,7,8]);
          materialChart.draw(view, materialOptions);
         }
         }
         var button = document.getElementById('addData');
         var show_inceptionv2 = document.getElementById("show_inceptionv2");
         button.onclick = function() {
         show_inceptionv2.onclick = function() {
          //data.removeRow(0);
          //data.removeColumn(2);
          //view = new google.visualization.DataView(data);
           view.setColumns([0,3,4]);
           view.setColumns([0,3,4]);
           view.hideColumns([1]);
           view.hideColumns([1,2,5,6,7,8]);
          view.hideColumns([2]);
           materialChart.draw(view, materialOptions);
           materialChart.draw(view, materialOptions);
          //data.insertRows(0, [['Test-A-changed', 14, 13]]);
          //drawMaterialChart();
         }
         }
         var showFPS_only = document.getElementById("showFPS");
        var show_inceptionv3 = document.getElementById('show_inceptionv3');
        show_inceptionv3.onclick = function() {
          view.setColumns([0,5,6]);
          view.hideColumns([1,2,3,4,7,8]);
          materialChart.draw(view, materialOptions);
        }
        var show_inceptionv4 = document.getElementById("show_inceptionv4");
        show_inceptionv4.onclick = function() {
          view.setColumns([0,7,8]);
          view.hideColumns([1,2,3,4,5,6]);
          materialChart.draw(view, materialOptions);
        }
        /*Select the backend to filter the data to show in the chart*/
        var button = document.getElementById('show_tensorflow');
        button.onclick = function() {
          view1.setColumns([0,1,2,3,4,5,6]);
          view1.hideColumns([7,8,9,10,11,12]);
          materialChart1.draw(view1, materialOptions1);
        }
         var showFPS_only = document.getElementById("show_tflite");
         showFPS_only.onclick = function() {
         showFPS_only.onclick = function() {
           //view = new google.visualization.DataView(data);
           view1.setColumns([0,7,8,9,10,11,12]);
           view.setColumns([0,1,2]);
          view1.hideColumns([1,2,3,4,5,6]);
           view.hideColumns([3]);
          materialChart1.draw(view1, materialOptions1);
           view.hideColumns([4]);
        }
           materialChart.draw(view, materialOptions);
        /*Select the Platform to filter the data to show in the chart*/
        var show_x86 = document.getElementById('show_x86');
        show_x86.onclick = function() {
           view2.setColumns([0,1,7]);
          view2.hideColumns([2,3,4,5,6,8,9,10,11,12]);
           materialChart2.draw(view2, materialOptions2);
        }
        var show_x86_gpu = document.getElementById("show_x86_gpu");
        show_x86_gpu.onclick = function() {
          view2.setColumns([0,2,8]);
          view2.hideColumns([1,3,4,5,6,7,9,10,11,12]);
           materialChart2.draw(view2, materialOptions2);
        }
        var show_tx2 = document.getElementById('show_tx2');
        show_tx2.onclick = function() {
          view2.setColumns([0,3,9]);
          view2.hideColumns([1,2,4,5,6,7,8,10,11,12]);
           materialChart2.draw(view2, materialOptions2);
         }
         }
          function show_0() {
        var show_tx2_gpu = document.getElementById("show_tx2_gpu");
          //view = new google.visualization.DataView(data);
        show_tx2_gpu.onclick = function() {
          if (check_box.checked == false){
          view2.setColumns([0,4,10]);
            view.hideRows([0]);
           view2.hideColumns([1,2,3,5,6,7,8,9,11,12]);
            materialChart.draw(view, materialOptions);
           materialChart2.draw(view2, materialOptions2);
            //show_1();
           }else{
            view.setRows([0,1,2,3,4,5]);
            materialChart.draw(view, materialOptions);
            //show_1();
          }
         
          //view.setColumns([0,1,2]);
          //view.hideColumns([3]);
          //view.hideColumns([4]);
           //materialChart.draw(view, materialOptions);
         }
         }
          
         var show_coral = document.getElementById('show_coral');
        function show_1() {
        show_coral.onclick = function() {
          //view = new google.visualization.DataView(data);
          view2.setColumns([0,5,11]);
          if (check_box2.checked == false){
           view2.hideColumns([1,2,3,4,6,7,8,9,10,12]);
            view.hideRows([1]);
           materialChart2.draw(view2, materialOptions2);
            materialChart.draw(view, materialOptions);
           
           }else{
            view.setRows([0,1,2,3,4,5]);
            materialChart.draw(view, materialOptions);
            //show_0();
          }
          //show_0();
          //view.setColumns([0,1,2]);
          //view.hideColumns([3]);
          //view.hideColumns([4]);
           //materialChart.draw(view, materialOptions);
         }
         }
        drawMaterialChart();
         var show_coral_tpu = document.getElementById("show_coral_tpu");
         var hideSal = document.getElementById("reset");
         show_coral_tpu.onclick = function() {
         hideSal.onclick = function() {
           view2.setColumns([0,6,12]);
           view.setRows([0,1,2,3,4,5]);
           view2.hideColumns([1,2,3,4,5,7,8,9,10,11]);
           view.setColumns([0,1,2,3,4,]);
          materialChart2.draw(view2, materialOptions2);
            materialChart.draw(view, materialOptions);
          //drawMaterialChart();
         }
         }
         drawMaterialChart();
         drawMaterialChart();
     };
     };

Revision as of 15:19, 26 March 2020




Previous: Example Applications/DispTec Index Next: Model Zoo


GstInference
GstInference
Introduction
Getting started
Supported architectures

InceptionV1

InceptionV3

YoloV2

AlexNet
Supported backends

Caffe

Metadata and Signals
Overlay Elements
Utils Elements
Legacy pipelines
Example pipelines
Example applications
Benchmarks
Model Zoo
Project Status
Contact Us

Coral from Google



GstInference Benchmarks

The following benchmarks were run with a source video (1920x1080@60). With the following base GStreamer pipeline, and environment variables: 

$ VIDEO_FILE='video.mp4'
$ MODEL_LOCATION='graph_inceptionv1_tensorflow.pb'
$ INPUT_LAYER='input'
$ OUTPUT_LAYER='InceptionV1/Logits/Predictions/Reshape_1'

The environment variables were changed accordingly with the used model (Inception V1,V2,V3 or V4) 

GST_DEBUG=inception1:1 gst-launch-1.0 filesrc location=$VIDEO_FILE ! decodebin ! videoconvert ! videoscale ! queue ! net.sink_model inceptionv1 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER net.src_model ! perf ! fakesink -v

The Desktop PC had the following specifications:

  • Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz
  • 8 GB RAM
  • Cedar [Radeon HD 5000/6000/7350/8350 Series]
  • Linux 4.15.0-54-generic x86_64 (Ubuntu 16.04)

The Jetson Xavier power modes used were 2 and 6 (more information: Supported Modes and Power Efficiency)

  • View current power mode:
$ sudo /usr/sbin/nvpmodel -q
  • Change current power mode:
sudo /usr/sbin/nvpmodel -m x

Where x is the power mode ID (e.g. 0, 1, 2, 3, 4, 5, 6).

Summary

Desktop PC CPU Library
Model Framerate CPU Usage
Inception V1 11.89 48
Inception V2 10.33 65
Inception V3 5.41 90
Inception V4 3.81 94
Jetson Xavier (15W) CPU Library GPU Library
Model Framerate CPU Usage Framerate CPU Usage
Inception V1 8.24 86 52.3 43
Inception V2 6.58 88 39.6 42
Inception V3 2.54 92 17.8 25
Inception V4 1.22 94 9.4 20
Jetson Xavier (30W) CPU Library GPU Library
Model Framerate CPU Usage Framerate CPU Usage
Inception V1 6.41 93 66.27 72
Inception V2 5.11 95 50.59 62
Inception V3 1.96 98 22.95 44
Inception V4 0.98 99 12.14 32

Framerate

thumb
thumb

CPU Usage

thumb
thumb

TensorFlow Lite Benchmarks








Previous: Example Applications/DispTec Index Next: Model Zoo



Retrieved from "https://developer.ridgerun.com/wiki/index.php?title=GstInference/Benchmarks&oldid=28491"