Skip to content

Appendix A. Specifications#

Classification performance#

Classification performance was measured on a two datasets:

  • Cooperative dataset (containing 20K images from various sources obtained at several banks);
  • Non cooperative dataset (containing 20K).

The two tables below contain true positive rates corresponding to select false positive rates.

"Classification performance @ low FPR on cooperative dataset"

FPR TPR CNN 54 TPR CNN 56 TPR CNN 57 TPR CNN 58 TPR CNN 59 TPR CNN 54m TPR CNN 56m TPR CNN 59m TPR CNN 60 TPR CNN 60m
10^-7^ 0.9765 0.9907 0.9906 0.9910 0.9911 0.9699 0.9652 0.9876 0.9917 0.9660
10^-6^ 0.9849 0.9914 0.9915 0.9916 0.9915 0.9829 0.9814 0.9904 0.9917 0.9824
10^-5^ 0.9892 0.9916 0.9917 0.9918 0.9919 0.9887 0.9886 0.9915 0.9919 0.9889
10^-4^ 0.9909 0.9917 0.9918 0.9919 0.9921 0.9910 0.9910 0.9919 0.9921 0.9909

"Classification performance @ low FPR on non cooperative dataset"

FPR TPR CNN 54 TPR CNN 56 TPR CNN 57 TPR CNN 58 TPR CNN 59 TPR CNN 54m TPR CNN 56m TPR CNN 59m TPR CNN 60 TPR CNN 60m
10^-7^ 0.9638 0.9698 0.9723 0.9767 0.9832 0.8813 0.8844 0.9377 0.9893 0.8797
10^-6^ 0.9773 0.9809 0.9817 0.9839 0.9880 0.9233 0.9229 0.9629 0.9914 0.9246
10^-5^ 0.9852 0.9871 0.9873 0.9880 0.9908 0.9538 0.9561 0.9794 0.9914 0.9595
10^-4^ 0.9896 0.9902 0.9905 0.9909 0.9924 0.9752 0.9757 0.9880 0.9925 0.9821

Runtime performance for CentOS Linux environment#

Face detection performance depends on input image parameters such as resolution and bit depth as well as the size of the detected face.

Input data characteristics:

  • Image resolution: 1920x1080px;
  • Image format: 24 BPP RGB;

Performance measurements are presented for CPU, GPU and NPU execution modes in tables below. Measured values are averages of at least 100 experiments.

Estimated values of memory consumption are also presented for CPU and GPU. These values are highly depend on the input data and the conditions of the experiment.

The results for minimum batch size and optimal batch size are shown in the tables below. All the intermediate and non-optimal values are omitted.

Face detections are performed using FaceDetV3 NN.

All types of face detection and redetect performed with capturing bounding boxes and 5 facial landmarks.

CPU performance#

Benchmarking for CPU was performed on the server with the following hardware configuration:

CPU:

  • Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz;
  • CPU(s): 40
  • Thread(s) per core: 2
  • Core(s) per socket: 10
  • Socket(s): 2
  • NUMA node(s): 2
  • CPU with AVX2 instruction set was used

OS: CentOS Linux release 8.3.2011

RAM: 128 GB DDR4 (Clock Speed: 2133 MHz)

In experiments listed in tables below face detection and descriptor extraction algorithms used all available CPU cores, whereas matching performance is specified per-core.

Descriptor matching is only implemented on CPU.

CPU. Detector performance#

The table below shows the performance of Detector on the CPU.

Measurement CPU threads BatchSize Average (ms) RAM Memory (Mb)
Detector (minFaceSize=20) 1 1 373.92 1889.0
Detector (minFaceSize=20) 8 1 152.73 2076.0
Detector (minFaceSize=20) 8 4 147.26 4411.0
Detector (minFaceSize=20) 8 8 148.32 7329.0
Detector (minFaceSize=50) 1 1 63.23 1261.0
Detector (minFaceSize=50) 8 1 27.52 1482.0
Detector (minFaceSize=50) 8 4 23.43 1810.0
Detector (minFaceSize=50) 8 8 24.61 2358.0
Detector (minFaceSize=90) 1 1 23.11 1184.0
Detector (minFaceSize=90) 8 1 11.62 1364.0
Detector (minFaceSize=90) 8 4 8.03 1470.0
Detector (minFaceSize=90) 8 8 8.23 1748.0
Redetect 1 1 0.63 1252.0
Redetect 8 1 0.83 1284.0
Redetect 8 4 0.32 1673.0
Redetect 8 8 0.25 2153.0
FaceLandmarks5Detector 1 1 0.22 1225.0
FaceLandmarks5Detector 8 1 0.37 1225.0
FaceLandmarks5Detector 8 8 0.09 1226.0
FaceLandmarks68Detector 1 1 3.2 1226.0
FaceLandmarks68Detector 8 1 2.0 1230.0
FaceLandmarks68Detector 8 8 1.0 1237.0

CPU. HumanDetector performance#

The table below shows the performance of HumanDetector on the CPU.

Measurement CPU threads BatchSize Average (ms) RAM Memory (Mb)
HumanDetector (imageSize=320) 1 1 10.27 1697.0
HumanDetector (imageSize=320) 8 1 6.63 1869.0
HumanDetector (imageSize=320) 8 8 4.01 2009.0
HumanDetector (imageSize=640) 1 1 36.06 1714.0
HumanDetector (imageSize=640) 8 1 16.89 1797.0
HumanDetector (imageSize=640) 8 8 15.07 2337.0
HumanLandmarksDetector 1 1 32.3 1270.0
HumanLandmarksDetector 8 1 13.8 1384.0
HumanLandmarksDetector 8 4 8.8 1688.0
HumanLandmarksDetector 8 8 8.4 1831.0
HumanRedetect 1 1 2.61 1239.0
HumanRedetect 8 1 2.76 1545.0
HumanRedetect 8 4 1.24 1770.0
HumanRedetect 8 8 1.26 1987.0

CPU. HumanFaceDetector performance#

The table below shows the performance of HumanFaceDetector on the CPU.

Measurement CPU threads BatchSize Average (ms) RAM Memory (Mb)
HumanFaceDetector (minFaceSize=20) 1 1 425.37 2558
HumanFaceDetector (minFaceSize=20) 8 1 183.5 2600
HumanFaceDetector (minFaceSize=20) 8 8 182.35 9340
HumanFaceDetector (minFaceSize=50) 1 1 66.97 1783
HumanFaceDetector (minFaceSize=50) 8 1 28.9 1812
HumanFaceDetector (minFaceSize=50) 8 8 29.17 2900
HumanFaceDetector (minFaceSize=90) 1 1 22.6 1734
HumanFaceDetector (minFaceSize=90) 8 1 10.71 1758
HumanFaceDetector (minFaceSize=90) 8 8 9.17 2072

CPU. HeadDetector performance#

The table below shows the performance of HeadDetector on the CPU.

Measurement CPU threads BatchSize Average (ms) RAM Memory (Mb)
HeadDetector (minHeadSize=20) 1 1 361.9 2374
HeadDetector (minHeadSize=20) 8 1 158.72 2423
HeadDetector (minHeadSize=20) 8 8 153.9 7710
HeadDetector (minHeadSize=50) 1 1 59.02 1754
HeadDetector (minHeadSize=50) 8 1 26.18 1801
HeadDetector (minHeadSize=50) 8 8 25.43 2797
HeadDetector (minHeadSize=90) 1 1 21.08 1731
HeadDetector (minHeadSize=90) 8 1 10.9 1778
HeadDetector (minHeadSize=90) 8 8 8.34 2168

CPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the CPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement CPU threads BatchSize Average (ms) RAM Memory (Mb)
Eyes (INFRA_RED, useStatusPlan=0) 1 1 0.6 1184.0
Eyes (INFRA_RED, useStatusPlan=0) 8 1 0.4 1204.0
Eyes (INFRA_RED, useStatusPlan=0) 8 8 0.3 1202.0
Eyes (RGB, useStatusPlan=0) 1 1 1.2 1237.0
Eyes (RGB, useStatusPlan=0) 8 1 0.8 1259.0
Eyes (RGB, useStatusPlan=0) 8 8 0.5 1258.0
Eyes (INFRA_RED, useStatusPlan=1) 1 1 0.6 1187.0
Eyes (INFRA_RED, useStatusPlan=1) 8 1 0.4 1207.0
Eyes (INFRA_RED, useStatusPlan=1) 8 8 0.3 1205.0
Eyes (RGB, useStatusPlan=1) 1 1 1.1 1241.0
Eyes (RGB, useStatusPlan=1) 8 1 0.8 1257.0
Eyes (RGB, useStatusPlan=1) 8 8 0.5 1255.0
Infra-Red 1 1 2 1191.0
Infra-Red 8 1 1.0 1209.0
Infra-Red 8 8 0.7 1218.0
AGS 1 1 0.3 1242.0
AGS 8 1 0.2 1259.0
AGS 8 8 0.07 1303.0
HeadPoseByImage 1 1 0.3 1188.0
HeadPoseByImage 8 1 0.3 1220.0
HeadPoseByImage 8 8 0.09 1252.0
Warper 1 1 2.1 1180.0
Warper 8 1 2.2 1219.0
Warper 8 8 0.9 1230.0
Child 1 1 18.7 1263.0
Child 8 1 6.3 1281.0
Child 8 8 5.2 1297.0
BlackWhite 1 1 1.3 1249.0
BlackWhite 8 1 0.7 1265.0
BlackWhite 8 8 1.2 1263.0
BestShotQuality 1 1 0.3 1238.0
BestShotQuality 8 1 0.2 1259.0
BestShotQuality 8 8 0.08 1299.0
MedicalMask 1 1 5.6 1258.0
MedicalMask 8 1 3.2 1287.0
MedicalMask 8 8 2.8 1318.0
LivenessOneShotRGBEstimator 1 1 246.17 1909.0
LivenessOneShotRGBEstimator 8 1 71.6 2030.0
LivenessOneShotRGBEstimator 8 8 77.31 3155.0
Orientation 1 1 5.06 1609.0
Orientation 8 1 3.33 1682.0
Orientation 8 8 1.86 1875.0
CredibilityCheck 1 1 120.3 1332.0
CredibilityCheck 8 1 35.1 1351.0
CredibilityCheck 8 8 34.1 1558.0
FacialHair 1 1 12.86 1751.0
FacialHair 8 1 4.84 1770.0
FacialHair 8 8 4.24 1794.0
PortraitStyle 1 1 1.54 1738.0
PortraitStyle 8 1 2.2 1846.0
PortraitStyle 8 8 0.95 1915.0
Background 1 1 1.1 1239.0
Background 8 1 1.2 1258.0
Background 8 8 1.7 1305.0
NaturalLight 1 1 2.37 1250.0
NaturalLight 8 1 1.49 1267.0
NaturalLight 8 8 1.97 1276.0
FishEye 1 1 12.8 1747.0
FishEye 8 1 4.8 1747.0
FishEye 8 8 0.6 1771.0
RedEye 1 1 5.7 1241.0
RedEye 8 1 1.9 1260.0
RedEye 8 8 1.6 1264.0
HeadWear 1 1 4.09 1742.0
HeadWear 8 1 2.63 1769.0
HeadWear 8 8 1.2 1773.0
EyeBrowEstimator 1 1 13.06 1751.0
EyeBrowEstimator 8 1 4.82 1769.0
EyeBrowEstimator 8 8 4.27 1781.0
HumanAttributeEstimator 1 1 11.93 1624.0
HumanAttributeEstimator 8 1 5.83 1651.0
HumanAttributeEstimator 8 8 3.78 1699.0
Mouth 1 1 6.64 1252.0
Mouth 8 1 2.64 1271.0
Mouth 8 8 2.12 1290.0
CrowdEstimator (Single, minHeadSize=6) 1 1 6115.94 3133
CrowdEstimator (Single, minHeadSize=6) 8 1 1577.25 3164
CrowdEstimator (Single, minHeadSize=6) 8 8 1454.59 12200
CrowdEstimator (Single, minHeadSize=12) 1 1 1534.97 2205
CrowdEstimator (Single, minHeadSize=12) 8 1 389.63 2232
CrowdEstimator (Single, minHeadSize=12) 8 8 368.08 4481
CrowdEstimator (TwoNets, minHeadSize=6) 1 1 6208.43 3184
CrowdEstimator (TwoNets, minHeadSize=6) 8 1 1600.78 3400
CrowdEstimator (TwoNets, minHeadSize=6) 8 8 1480.87 16651
CrowdEstimator (TwoNets, minHeadSize=12) 1 1 1568.06 2274
CrowdEstimator (TwoNets, minHeadSize=12) 8 1 394.9 2373
CrowdEstimator (TwoNets, minHeadSize=12) 8 8 371.6 5220
DynamicRange 1 1 1.49 1721
DynamicRange 8 1 1.61 1749
DynamicRange 8 8 0.81 1793

CPU. Estimations performance without batch interface#

The table below shows the performance of Estimations on the CPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement CPU threads Average (ms) RAM Memory (Mb)
EyesGaze 1 2.2 1250
EyesGaze 8 1.4 1270
Emotions 1 13.6 1262
Emotions 8 4.9 1275
Attributes 1 63.3 1265
Attributes 8 19.8 1291
Quality 1 1.2 1178
Quality 8 0.6 1220
Overlap 1 4.5 1248
Overlap 8 1.3 1267
Glasses 1 1.8 1240
Glasses 8 0.8 1264
PPE 1 10.04 1695
PPE 8 4.71 1718
LivenessFlyingFaces 1 15.07 1804
LivenessFlyingFaces 8 7.21 1913
LivenessRGBMEstimator 1 30.6 1245
LivenessRGBMEstimator 8 9.7 1265
LivenessFPR 1 44.2 1263
LivenessFPR 8 19.9 1293

CPU. Extractor performance#

The table below shows the performance of Extractor on the CPU.

Model CPU threads Batch Size Average (ms) RAM Memory (Mb)
57 1 1 221.2 1475
57 8 8 58.3 1551
58 1 1 219.3 1470
58 8 8 58.0 1543
59 1 1 219.7 1473
59 8 8 58.2 1550
60 1 1 258.0 1473
60 8 8 51.1 1550
102 1 1 1.8 1149
102 8 8 2.1 1190
103 1 1 142.2 1459
103 8 8 50.6 1494
104 1 1 12.6 1186
104 8 8 6.2 1243
105 1 1 1.68 1590
105 8 8 0.69 1644
106 1 1 138.48 1877
106 8 8 38.74 1931
107 1 1 11.82 1625
107 8 8 3.7 1709

CPU. Matcher performance#

The table below shows the performance of Matcher on the CPU. The table includes average matcher per second for descriptors received using the following CNN model versions:

  • face descriptors: 57, 58, 59
  • human body descriptors: 102, 103, 104, 105, 106, 107
Model CPU threads Batch Size Average (matches/sec) RAM Memory (Mb)
57 1 1000 28 M 20
58 1 1000 28 M 18
59 1 1000 28 M 15
60 1 1000 42.2 M 15.0
102 1 1000 10.17 M 16
103 1 1000 10.17 M 16
104 1 1000 10.17 M 20
105 1 1000 28.64 M 111
106 1 1000 28.64 M 106
107 1 1000 28.64 M 109

Note: The above value is the maximum performance of the matcher on a particular piece of hardware. Performance in general does not depend on the size of the batch, but may be limited by memory performance at large values of the batch size.

GPU performance#

Benchmarking for GPU was performed on the following hardware configuration:

GPU: NVIDIA Tesla T4.

OS: CentOS Linux release 8.3.2011

GPU. Detector performance#

The table below shows the performance of Detector on the GPU.

Measurement Batch Size Average (ms) GPU Memory (Mb) RAM Memory (Mb)
Detector (minFaceSize=20) 1 29.02 1485.0 1663.0
Detector (minFaceSize=20) 4 34.37 3611.0 1691.0
Detector (minFaceSize=20) 8 38.09 6539.0 1741.0
Detector (minFaceSize=50) 1 7.46 847.0 1653.0
Detector (minFaceSize=50) 4 6.56 1207.0 1682.0
Detector (minFaceSize=50) 8 6.24 1779.0 1702.0
Detector (minFaceSize=90) 1 4.95 835.0 1655.0
Detector (minFaceSize=90) 4 3.44 907.0 1669.0
Detector (minFaceSize=90) 8 3.17 1381.0 1694.0
Redetect 1 2.52 847.0 1657.0
Redetect 4 1.64 1207.0 1660.0
Redetect 8 1.47 1779.0 1663.0
Redetect 16 1.38 2781.0 1667.0
FaceLandmarks5Detector 1 2.33 821.0 1651.0
FaceLandmarks5Detector 8 0.32 821.0 1651.0
FaceLandmarks5Detector 16 0.17 821.0 1657.0
FaceLandmarks68Detector 1 2.6 821.0 1669.0
FaceLandmarks68Detector 8 1.5 821.0 1668.3
FaceLandmarks68Detector 16 1.4 949.0 1663.0

GPU. HumanDetector performance#

The table below shows the performance of HumanDetector on the GPU.

Measurement Batch Size Average (ms) GPU Memory (Mb) RAM Memory (Mb)
HumanDetector (imageSize=320) 1 4.38 907.0 1672.0
HumanDetector (imageSize=320) 4 2.52 993.0 1690.0
HumanDetector (imageSize=320) 8 2.27 937.0 1729.0
HumanDetector (imageSize=640) 1 5.41 875.0 1687.0
HumanDetector (imageSize=640) 4 4.53 1265.0 1708.0
HumanDetector (imageSize=640) 8 4.36 1277.0 1730.0
HumanLandmarksDetector 1 11.0 821.0 821.0
HumanLandmarksDetector 4 4.0 1013.0 965.0
HumanLandmarksDetector 8 3.0 1283.0 1109.0
HumanRedetect 1 2.74 789.0 1696.0
HumanRedetect 4 1.67 1013.0 1695.0
HumanRedetect 8 1.47 1251.0 1689.0
HumanRedetect 16 1.4 1867.0 1709.0

GPU. HeadDetector performance#

The table below shows the performance of HeadDetector on the GPU.

Measurement Batch Size Average (ms) GPU Memory (Mb) RAM Memory (Mb)
HeadDetector (minHeadSize=20) 1 28.29 1533 1679
HeadDetector (minHeadSize=20) 4 33.81 3691 1698
HeadDetector (minHeadSize=20) 8 37.59 6623 1755
HeadDetector (minHeadSize=50) 1 7.07 915 1668
HeadDetector (minHeadSize=50) 4 6.42 1255 1687
HeadDetector (minHeadSize=50) 8 6.11 1827 1713
HeadDetector (minHeadSize=90) 1 4.75 915 1674
HeadDetector (minHeadSize=90) 4 3.27 955 1684
HeadDetector (minHeadSize=90) 8 3.03 1129 1714

GPU. HumanFace detector performance#

The table below shows the performance of HumanFaceDetector on the GPU.

Measurement Batch Size Average (ms) GPU Memory (Mb) RAM Memory (Mb)
HumanFaceDetector (minFaceSize=20) 1 34.1 1675.0 1703.0
HumanFaceDetector (minFaceSize=20) 4 42.6 4415.0 1774.0
HumanFaceDetector (minFaceSize=20) 8 50.32 8041.0 1889.0
HumanFaceDetector (minFaceSize=50) 1 7.99 903.0 1674.0
HumanFaceDetector (minFaceSize=50) 4 7.15 1487.0 1706.0
HumanFaceDetector (minFaceSize=50) 8 6.83 2067.0 1764.0
HumanFaceDetector (minFaceSize=90) 1 5.3 903.0 1672.0
HumanFaceDetector (minFaceSize=90) 4 3.52 929.0 1685.0
HumanFaceDetector (minFaceSize=90) 8 3.24 1125.0 1719.0

GPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the GPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement Batch Size Average (ms) GPU Memory (Mb) RAM Memory (Mb)
HeadPoseByImage 1 2.32 733.0 1679.0
HeadPoseByImage 32 1.43 923.0 1864.0
Warper 1 0.11 739.0 1672.0
Warper 32 0.03 931.0 1672.0
Eyes (INFRA_RED, useStatusPlan=0) 1 0.65 811.0 1668.0
Eyes (INFRA_RED, useStatusPlan=0) 16 0.23 811.0 1667.0
Eyes (INFRA_RED, useStatusPlan=0) 32 0.2 811.0 1674.0
Eyes (RGB, useStatusPlan=0) 1 1.19 821.0 1681.0
Eyes (RGB, useStatusPlan=0) 16 0.44 821.0 1669.0
Eyes (RGB, useStatusPlan=0) 32 0.43 853.0 1683.0
Eyes (INFRA_RED, useStatusPlan=1) 1 0.64 811.0 1666.0
Eyes (INFRA_RED, useStatusPlan=1) 16 0.23 811.0 1678.0
Eyes (INFRA_RED, useStatusPlan=1) 32 0.2 811.0 1672.0
Eyes (RGB, useStatusPlan=1) 1 0.66 821.0 1671.0
Eyes (RGB, useStatusPlan=1) 16 0.24 821.0 1673.0
Eyes (RGB, useStatusPlan=1) 32 0.23 853.0 1680.0
Infra-Red 1 1.11 811.0 1666.0
Infra-Red 32 0.54 811.0 1679.0
AGS 1 2.2 821.0 1676.0
AGS 16 1.46 917.0 1764.0
Child 1 2.66 853.0 1694.0
Child 16 1.11 963.0 1697.0
BlackWhite 1 1.05 821.0 1676.0
BlackWhite 16 0.4 853.0 1677.0
BestShotQuality 1 2.31 821.0 1677.0
BestShotQuality 16 1.45 917.0 1765.0
MedicalMask 1 5.01 821.0 1702.0
MedicalMask 16 1.69 917.0 1791.0
LivenessOneShotRGBEstimator 1 26.25 1316 1843.0
LivenessOneShotRGBEstimator 8 19.39 2364 1851.0
LivenessOneShotRGBEstimator 16 20.17 4016 1847.0
Orientation 1 3.12 799.0 1670.0
Orientation 16 1.73 963.0 1664.0
Orientation 32 1.69 1141.0 1669.0
CredibilityCheck 1 5.54 947.0 1774.0
CredibilityCheck 16 3.72 1339.0 1771.0
FacialHair 1 1.86 853.0 1687.0
FacialHair 16 0.32 853.0 1683.0
FacialHair 32 0.28 853.0 1685.0
PortraitStyle 1 2.84 895.0 1671.0
PortraitStyle 16 1.51 915.0 1770.0
PortraitStyle 32 1.48 1085.0 1861.0
Background 1 2.6 821.0 1679.0
Background 16 1.5 917.0 1770.0
NaturalLight 1 3.61 853.0 1692.0
NaturalLight 16 0.27 853.0 1695.0
FishEye 1 2.37 895.0 1692.0
FishEye 16 0.14 895.0 1694.0
RedEye 1 1.1 821.0 1675.0
RedEye 16 0.15 821.0 1675.0
HeadWear 1 4.14 853.0 1696.0
HeadWear 16 0.36 853.0 1699.0
HeadWear 32 0.27 853.0 1697.0
EyeBrowEstimator 1 2.56 895.0 1694.0
EyeBrowEstimator 16 0.8 895.0 1693.0
EyeBrowEstimator 32 0.76 803.0 1079.0
HumanAttributeEstimator 1 5.53 853.0 1691.0
HumanAttributeEstimator 16 0.57 853.0 1722.0
Mouth 1 4.03 853.0 1690.0
Mouth 16 0.42 949.0 1691.0
Mouth 32 0.37 1043.0 1690.0
CrowdEstimator (Single, minHeadSize=6) 1 162.51 2583 2101
CrowdEstimator (Single, minHeadSize=6) 4 172.04 6599 2101
CrowdEstimator (Single, minHeadSize=6) 8 172.38 11683 2100
CrowdEstimator (Single, minHeadSize=12) 1 50.93 2337 2091
CrowdEstimator (Single, minHeadSize=12) 4 42.02 2635 2100
CrowdEstimator (Single, minHeadSize=12) 8 44.09 4405 2096
CrowdEstimator (TwoNets, minHeadSize=6) 1 173.88 3003 2110
CrowdEstimator (TwoNets, minHeadSize=6) 4 186.91 7543 2102
CrowdEstimator (TwoNets, minHeadSize=6) 8 189.06 13507 2098
CrowdEstimator (TwoNets, minHeadSize=12) 1 55.91 2651 2106
CrowdEstimator (TwoNets, minHeadSize=12) 4 45.5 2905 2110
CrowdEstimator (TwoNets, minHeadSize=12) 8 50.0 4865 2108

GPU. Estimations performance without batch interface#

The table below shows the performance of Estimations on the GPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement Average (ms) GPU Memory (Mb) RAM Memory (Mb)
EyesGaze 1.65 821 1675
Emotions 1.99 821 1689
Attributes 4.95 815 1717
Quality 0.98 731 1665
Overlap 1.23 821 1688
PPE 4.66 869 1696
Glasses 1.01 821 1679
LivenessFlyingFaces 6.39 927 1694
LivenessRGBMEstimator 6.96 821 1674
LivenessFPR 12.56 885 1697

GPU. Extractor performance#

The table below shows the performance of Extractor on the GPU.

Model Batch Size Average (ms) GPU Memory (Mb) RAM Memory (Mb)
57 1 10.2 929.0 1841
57 16 6.5 1341.0 1834
58 1 10.2 989.0 1835
58 16 6.4 1781.0 1825
59 1 10.2 929.0 1833
59 16 6.4 1341.0 1837
60 1 16.0 931.0 1840
60 16 8.9 1343.0 1845
102 1 3.7 733.0 1659
102 16 0.3 763.0 1658
103 1 7.2 913.0 1817
103 16 3.7 1279.0 1821
104 1 4.5 759.0 1686
104 16 0.6 865.0 1690
105 1 3.93 781 1664
105 16 0.31 811 1664
106 1 6.84 949 1884
106 16 3.55 1315 1879
107 1 4.38 803 1691
107 16 0.59 907 1684

NPU Performance#

Benchmarking for NPU was performed on the server with the following hardware configuration:

NPU: Huawei Atlas 300I (inference card).

OS: Ubuntu 18.04

CPU: Intel(R) Xeon(R) Gold 5118 CPU @ 2.30GHz x 48

RAM: 64GB

NPU. Detector performance#

The table below shows the performance of Detector on the NPU.

Measurement BatchSize Average (ms)
Detector (minFaceSize=20) 1 24.4
Detector (minFaceSize=20) 4 18.01
Detector (minFaceSize=20) 8 17.73
Detector (minFaceSize=50) 1 24.53
Detector (minFaceSize=50) 4 18.0
Detector (minFaceSize=50) 8 17.74
Detector (minFaceSize=90) 1 24.44
Detector (minFaceSize=90) 4 17.91
Detector (minFaceSize=90) 8 17.44
Redetect 1 7.56
Redetect 8 4.31
Redetect 16 4.08

NPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the NPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement BatchSize Average (ms)
HeadPoseByImage 1 8.0
HeadPoseByImage 16 4.2
HeadPoseByImage 32 3.9
AGS 1 6.6
AGS 16 3.7
AGS 32 3.7
BestShotQuality 1 15.6
BestShotQuality 16 7.8
BestShotQuality 32 7.6
MedicalMask 1 6.1
MedicalMask 16 3.8
MedicalMask 32 3.7

NPU. Estimations performance without batch interface#

The table below shows the performance of Estimations on the NPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement Average (ms)
Warper 2.1

NPU. Extractor performance#

The table below shows the performance of Extractor on the NPU.

Type Model Batch Size Average (ms)
Extractor 57 1 10.9
Extractor 57 16 7.4

Runtime performance for macOS environment#

Face detection performance depends on input image parameters such as resolution and bit depth as well as the size of the detected face.

Input data characteristics:

  • Image resolution: 1920x1080px;
  • Image format: 24 BPP RGB;

Performance measurements are presented for CPU execution modes in tables below. Measured values are averages of at least 1000 experiments.

The results for minimum batch size and optimal batch size are shown in the tables below. All the intermediate and non-optimal values are omitted.

Face detections are performed using FaceDetV3 NN.

Intel-based processor performance (x86_64)#

Benchmarking for CPU was performed on the device with the following configuration:

Hardware Overview:

  • Model Name: Mac mini
  • Processor Name: 6-Core Intel Core i5
  • Processor Speed: 3 GHz
  • Number of Processors: 1
  • Total Number of Cores: 6
  • Memory: 16 GB
  • CPU with AVX2 instruction set was used

OS: macOS 11.2.1

In experiments listed in tables below face detection and descriptor extraction algorithms used all available CPU cores, whereas matching performance is specified per-core.

Intel-based processor. Detector performance#

The table below shows the performance of Detector on the Intel-based processor.

Measurement CPU threads BatchSize Average (ms)
Detector (minFaceSize=20) 1 1 284.79
Detector (minFaceSize=20) 8 1 159.0
Detector (minFaceSize=20) 8 4 168.68
Detector (minFaceSize=20) 8 8 171.88
Detector (minFaceSize=50) 1 1 45.3
Detector (minFaceSize=50) 8 1 27.3
Detector (minFaceSize=50) 8 4 28.58
Detector (minFaceSize=50) 8 8 29.06
Detector (minFaceSize=90) 1 1 18.91
Detector (minFaceSize=90) 8 1 9.7
Detector (minFaceSize=90) 8 4 9.6
Detector (minFaceSize=90) 8 8 10.02
Redetect 1 1 0.75
Redetect 8 1 0.87
Redetect 8 4 0.28
Redetect 8 8 0.27
FaceLandmarks5Detector 1 1 0.2
FaceLandmarks5Detector 8 1 0.3
FaceLandmarks5Detector 8 8 0.1
FaceLandmarks68Detector 1 1 2.3
FaceLandmarks68Detector 8 1 1.7
FaceLandmarks68Detector 8 8 1.1

Intel-based processor. HumanDetector performance#

The table below shows the performance of HumanDetector on the Intel-based processor.

Measurement CPU threads BatchSize Average (ms)
HumanDetector (imageSize=320) 1 1 10.28
HumanDetector (imageSize=320) 8 1 4.55
HumanDetector (imageSize=320) 8 4 4.94
HumanDetector (imageSize=320) 8 8 4.84
HumanDetector (imageSize=640) 1 1 27.99
HumanDetector (imageSize=640) 8 1 15.12
HumanDetector (imageSize=640) 8 4 17.04
HumanDetector (imageSize=640) 8 8 17.98
HumanLandmarksDetector 1 1 22.5
HumanLandmarksDetector 8 1 10.5
HumanLandmarksDetector 8 4 9.8
HumanLandmarksDetector 8 8 9.8
HumanRedetect 1 1 3.69
HumanRedetect 8 1 1.96
HumanRedetect 8 4 1.21
HumanRedetect 8 8 1.33

Intel-based processor. HumanFaceDetector performance#

The table below shows the performance of HumanFaceDetector on the Intel-based processor.

Measurement CPU threads BatchSize Average (ms)
HumanFaceDetector (minFaceSize=20) 1 1 331.58
HumanFaceDetector (minFaceSize=20) 4 1 192.95
HumanFaceDetector (minFaceSize=20) 4 4 200.72
HumanFaceDetector (minFaceSize=20) 4 8 203.85
HumanFaceDetector (minFaceSize=50) 1 1 52.02
HumanFaceDetector (minFaceSize=50) 4 1 28.25
HumanFaceDetector (minFaceSize=50) 4 4 31.48
HumanFaceDetector (minFaceSize=50) 4 8 32.59
HumanFaceDetector (minFaceSize=90) 1 1 20.5
HumanFaceDetector (minFaceSize=90) 4 1 9.8
HumanFaceDetector (minFaceSize=90) 4 4 9.55
HumanFaceDetector (minFaceSize=90) 4 8 9.91

Intel-based processor. HeadDetector performance#

The table below shows the performance of HeadDetector on the Intel-based processor.

Measurement CPU threads BatchSize Average (ms)
HeadDetector (minHeadSize=20) 1 1 281.76
HeadDetector (minHeadSize=20) 8 1 150.13
HeadDetector (minHeadSize=20) 8 8 167.13
HeadDetector (minHeadSize=50) 1 1 44.18
HeadDetector (minHeadSize=50) 8 1 24.76
HeadDetector (minHeadSize=50) 8 8 28.49
HeadDetector (minHeadSize=90) 1 1 21.22
HeadDetector (minHeadSize=90) 8 1 7.92
HeadDetector (minHeadSize=90) 8 8 10.1

Intel-based processor. Estimations performance with batch interface#

The table below shows the performance of Estimations on the Intel-based processor for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement CPU threads BatchSize Average (ms)
HeadPoseByImage 1 1 0.21
HeadPoseByImage 8 1 0.17
HeadPoseByImage 8 8 0.07
Eyes (INFRA_RED, useStatusPlan=0) 1 1 0.45
Eyes (INFRA_RED, useStatusPlan=0) 8 1 0.29
Eyes (INFRA_RED, useStatusPlan=0) 8 8 0.23
Eyes (RGB, useStatusPlan=0) 1 1 0.85
Eyes (RGB, useStatusPlan=0) 8 1 0.58
Eyes (RGB, useStatusPlan=0) 8 8 0.48
Eyes (INFRA_RED, useStatusPlan=1) 1 1 0.85
Eyes (INFRA_RED, useStatusPlan=1) 8 1 0.57
Eyes (INFRA_RED, useStatusPlan=1) 8 8 0.47
Eyes (RGB, useStatusPlan=1) 1 1 0.85
Eyes (RGB, useStatusPlan=1) 8 1 0.58
Eyes (RGB, useStatusPlan=1) 8 8 0.47
Infra-Red 1 1 1.51
Infra-Red 8 1 0.71
Infra-Red 8 8 0.81
AGS 1 1 0.18
AGS 8 1 0.13
AGS 8 8 0.05
Child 1 1 12.22
Child 8 1 4.67
Child 8 8 6.37
BlackWhite 1 1 1.0
BlackWhite 8 1 0.4
BlackWhite 8 8 1.0
BestShotQuality 1 1 0.18
BestShotQuality 8 1 0.14
BestShotQuality 8 8 0.06
MedicalMask 1 1 4.15
MedicalMask 8 1 2.2
MedicalMask 8 8 2.2
LivenessOneShotRGBEstimator 1 1 180.7
LivenessOneShotRGBEstimator 8 1 78.65
LivenessOneShotRGBEstimator 8 8 90.68
Orientation 1 1 5.58
Orientation 8 1 3.07
Orientation 8 8 2.37
CredibilityCheck 1 1 2.37
CredibilityCheck 8 1 36.0
CredibilityCheck 8 8 37.9
PortraitStyle 1 1 1.97
PortraitStyle 8 1 2.0
PortraitStyle 8 8 1.09
Background 1 1 0.7
Background 8 1 0.7
Background 8 8 1.4
NaturalLight 1 1 2.9
NaturalLight 8 1 1.7
NaturalLight 8 8 1.8
FishEye 1 1 16.7
FishEye 8 1 4.0
FishEye 8 8 0.7
RedEye 1 1 7.5
RedEye 8 1 1.4
RedEye 8 8 1.5
HeadWear 1 1 3.07
HeadWear 8 1 2.07
HeadWear 8 8 1.07
EyeBrowEstimator 1 1 14.04
EyeBrowEstimator 8 1 6.06
EyeBrowEstimator 8 8 4.84
HumanAttributeEstimator 1 1 12.13
HumanAttributeEstimator 8 1 5.78
HumanAttributeEstimator 8 8 4.22
Mouth 1 1 5.24
Mouth 8 1 2.16
Mouth 8 8 2.36
DynamicRange 1 1 0.29
DynamicRange 8 1 0.3
DynamicRange 8 8 0.09

Intel-based processor. Estimations performance without batch interface#

The table below shows the performance of Estimations on the Intel-based processor for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement CPU threads Average (ms)
EyesGaze 1 1.7
EyesGaze 8 0.9
Emotions 1 10.5
Emotions 8 4.1
Attributes 1 49.4
Attributes 8 16.4
Quality 1 1.4
Quality 8 0.6
Warper 1 1.3
Warper 8 1.0
Overlap 1 3.4
Overlap 8 1.1
PPE 1 8.83
PPE 8 4.83
Glasses 1 1.3
Glasses 8 0.5
LivenessFlyingFaces 1 17.86
LivenessFlyingFaces 8 5.96
LivenessRGBMEstimator 1 20.4
LivenessRGBMEstimator 8 8.9
LivenessFPR 1 31.2
LivenessFPR 8 18.0

Intel-based processor. Extractor performance#

The table below shows the performance of Extractor on the Intel-based processor.

Model CPU threads Batch Size Average (ms)
57 1 1 169.3
57 8 8 60.7
58 1 1 168.9
58 8 8 63.8
59 1 1 168.8
59 8 8 68.6
102 1 1 2.4
102 8 8 1.56
103 1 1 113.2
103 8 8 44.9
104 1 1 10.8
104 8 8 9.21
105 1 1 2.73
105 8 8 1.45
106 1 1 139.81
106 8 8 45.25
107 1 1 15.91
107 8 8 4.22

Intel-based processor. Matcher performance#

The table below shows the performance of Matcher on the Intel-based processor. The table includes average matcher per second for descriptors received using CNN 57, 58, 59, 102, 103, 104, 105, 106, 107.

Model CPU threads Batch Size Average (matches/sec)
57, 58 1 10000 37.34 M
59 1 10000 28 M
102 1 10000 14.46 M
103 1 10000 9.26 M
104 1 10000 14.66 M
105, 106, 107 1 10000 28.64 M

Note: The above value is the maximum performance of the matcher on a particular piece of hardware. Performance in general does not depend on the size of the batch, but may be limited by memory performance at large values of the batch size.

ARM-based processor performance (aarch64)#

Benchmarking for CPU was performed on the device with the following configuration:

Hardware Overview:

  • Model Name: Mac mini
  • Chip: Apple M1
  • Total Number of Cores: 8 (4 performance and 4 efficiency)
  • Memory: 16 GB
  • AVX2 instruction is not available

OS: macOS 11.2

In experiments listed in tables below face detection and descriptor extraction algorithms used all available CPU cores, whereas matching performance is specified per-core.

ARM-based processor. Detector performance#

The table below shows the performance of Detector on the ARM-based processor.

Measurement CPU threads BatchSize Average (ms)
Detector (minFaceSize=20) 1 1 627.78
Detector (minFaceSize=20) 8 1 201.45
Detector (minFaceSize=20) 8 4 202.34
Detector (minFaceSize=20) 8 8 205.36
Detector (minFaceSize=50) 1 1 107.57
Detector (minFaceSize=50) 8 1 40.73
Detector (minFaceSize=50) 8 4 34.36
Detector (minFaceSize=50) 8 8 33.91
Detector (minFaceSize=90) 1 1 37.9
Detector (minFaceSize=90) 8 1 17.99
Detector (minFaceSize=90) 8 4 13.28
Detector (minFaceSize=90) 8 8 12.35
Redetect 1 1 1.01
Redetect 8 1 1.13
Redetect 8 4 0.55
Redetect 8 8 0.49
FaceLandmarks5Detector 1 1 0.4
FaceLandmarks5Detector 8 1 0.6
FaceLandmarks5Detector 8 8 0.2
FaceLandmarks68Detector 1 1 3.4
FaceLandmarks68Detector 8 1 2.3
FaceLandmarks68Detector 8 8 1.6

ARM-based processor. HumanDetector performance#

The table below shows the performance of HumanDetector on the ARM-based processor.

Measurement CPU threads BatchSize Average (ms)
HumanDetector (imageSize=320) 1 1 21.74
HumanDetector (imageSize=320) 8 1 11.47
HumanDetector (imageSize=320) 8 4 8.0
HumanDetector (imageSize=320) 8 8 1.15
HumanDetector (imageSize=640) 1 1 79.3
HumanDetector (imageSize=640) 8 1 30.38
HumanDetector (imageSize=640) 8 4 25.2
HumanDetector (imageSize=640) 8 8 24.77
HumanLandmarksDetector 1 1 47.0
HumanLandmarksDetector 8 1 29.6
HumanLandmarksDetector 8 4 23.7
HumanLandmarksDetector 8 8 20.5
HumanRedetect 1 1 3.51
HumanRedetect 8 1 2.31
HumanRedetect 8 4 1.67
HumanRedetect 8 8 1.51

ARM-based processor. HumanFaceDetector performance#

The table below shows the performance of HumanFaceDetector on the ARM-based processor.

Measurement CPU threads BatchSize Average (ms)
HumanFaceDetector (minFaceSize=20) 1 1 715.22
HumanFaceDetector (minFaceSize=20) 8 1 237.4
HumanFaceDetector (minFaceSize=20) 8 8 239.92
HumanFaceDetector (minFaceSize=50) 1 1 121.26
HumanFaceDetector (minFaceSize=50) 8 1 49.4
HumanFaceDetector (minFaceSize=50) 8 8 39.39
HumanFaceDetector (minFaceSize=90) 1 1 41.92
HumanFaceDetector (minFaceSize=90) 8 1 22.01
HumanFaceDetector (minFaceSize=90) 8 8 14.1

ARM-based processor. HeadDetector performance#

The table below shows the performance of HeadDetector on the ARM-based processor.

Measurement CPU threads BatchSize Average (ms)
HeadDetector (minHeadSize=20) 1 1 631.68
HeadDetector (minHeadSize=20) 8 1 207.81
HeadDetector (minHeadSize=20) 8 8 213.2
HeadDetector (minHeadSize=50) 1 1 108.83
HeadDetector (minHeadSize=50) 8 1 42.13
HeadDetector (minHeadSize=50) 8 8 34.64
HeadDetector (minHeadSize=90) 1 1 37.87
HeadDetector (minHeadSize=90) 8 1 18.67
HeadDetector (minHeadSize=90) 8 8 12.46

ARM-based processor. Estimations performance with batch interface#

The table below shows the performance of Estimations on the ARM-based processor for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement CPU threads BatchSize Average (ms)
HeadPoseByImage 1 1 0.41
HeadPoseByImage 8 1 0.35
HeadPoseByImage 8 8 0.19
Eyes (INFRA_RED, useStatusPlan=0) 1 1 0.92
Eyes (INFRA_RED, useStatusPlan=0) 8 1 0.59
Eyes (INFRA_RED, useStatusPlan=0) 8 8 0.4
Eyes (RGB, useStatusPlan=0) 1 1 1.07
Eyes (RGB, useStatusPlan=0) 8 1 0.63
Eyes (RGB, useStatusPlan=0) 8 8 0.48
Eyes (INFRA_RED, useStatusPlan=1) 1 1 1.07
Eyes (INFRA_RED, useStatusPlan=1) 8 1 0.63
Eyes (INFRA_RED, useStatusPlan=1) 8 8 0.48
Eyes (RGB, useStatusPlan=1) 1 1 2.06
Eyes (RGB, useStatusPlan=1) 8 1 1.24
Eyes (RGB, useStatusPlan=1) 8 8 0.95
Infra-Red 1 1 4.72
Infra-Red 8 1 2.4
Infra-Red 8 8 1.82
AGS 1 1 0.37
AGS 8 1 0.29
AGS 8 8 0.17
Child 1 1 39.43
Child 8 1 22.54
Child 8 8 18.1
BlackWhite 1 1 2.9
BlackWhite 8 1 1.3
BlackWhite 8 8 1.3
BestShotQuality 1 1 0.39
BestShotQuality 8 1 0.31
BestShotQuality 8 8 0.18
MedicalMask 1 1 12.5
MedicalMask 8 1 6.28
MedicalMask 8 8 4.53
LivenessOneShotRGBEstimator 1 1 648.45
LivenessOneShotRGBEstimator 8 1 156.36
LivenessOneShotRGBEstimator 8 8 153.41
Orientation 1 1 10.28
Orientation 8 1 5.93
Orientation 8 8 3.51
CredibilityCheck 1 1 296.2
CredibilityCheck 8 1 103.2
CredibilityCheck 8 8 105.9
PortraitStyle 1 1 2.66
PortraitStyle 8 1 3.32
PortraitStyle 8 8 1.86
Background 1 1 2.4
Background 8 1 2.3
Background 8 8 2.1
NaturalLight 1 1 5.2
NaturalLight 8 1 2.9
NaturalLight 8 8 2.6
FishEye 1 1 35.7
FishEye 8 1 13.2
FishEye 8 8 1.7
RedEye 1 1 10.5
RedEye 8 1 3.3
RedEye 8 8 3.0
HeadWear 1 1 8.07
HeadWear 8 1 6.45
HeadWear 8 8 2.76
EyeBrowEstimator 1 1 35.77
EyeBrowEstimator 8 1 13.34
EyeBrowEstimator 8 8 10.5
HumanAttributeEstimator 1 1 28.09
HumanAttributeEstimator 8 1 14.91
HumanAttributeEstimator 8 8 9.02
Mouth 1 1 16.26
Mouth 8 1 7.86
Mouth 8 8 5.36
DynamicRange 1 1 0.28
DynamicRange 8 1 0.29
DynamicRange 8 8 0.16

ARM-based processor. Estimations performance without batch interface#

The table below shows the performance of Estimations on the ARM-based processor for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Measurement CPU threads Average (ms)
EyesGaze 1 5.3
EyesGaze 8 3.0
Emotions 1 36.9
Emotions 8 15.8
Attributes 1 154.9
Attributes 8 58.0
Quality 1 2.1
Quality 8 1.2
Warper 1 0.9
Warper 8 1.9
Overlap 1 9.0
Overlap 8 3.6
PPE 1 22.33
PPE 8 13.12
Glasses 1 4.3
Glasses 8 2.2
LivenessFlyingFaces 1 24.55
LivenessFlyingFaces 8 10.85
LivenessRGBMEstimator 1 51.5
LivenessRGBMEstimator 8 30.6
LivenessFPR 8 103.7
LivenessFPR 8 56.3

ARM-based processor. Extractor performance#

The table below shows the performance of Extractor on the ARM-based processor.

Type Model CPU threads Average (ms)
Extractor 57 1 547.2
Extractor 57 8 189.3
Extractor 58 1 547.2
Extractor 58 8 189.2
Extractor 59 1 535.6
Extractor 59 8 188.6

ARM-based processor. Matcher performance#

The table below shows the performance of Matcher on the ARM-based processor. The table includes average matcher per second for descriptors received using CNN 57, 58 and 59.

Type Model CPU threads Batch Size Average (matches/sec)
Matcher 57, 58 1 10000 2.08 M
Matcher 59 1 10000 2.08 M

Note: The above value is the maximum performance of the matcher on a particular piece of hardware. Performance in general does not depend on the size of the batch, but may be limited by memory performance at large values of the batch size.

Runtime performance for embedded environment#

Face detection performance depends on input image parameters such as resolution and bit depth as well as the size of the detected face.

Input data characteristics:

  • Image resolution: 640x480px;
  • Image format: 24 BPP RGB;

The results for minimum batch size and optimal batch size are shown in the tables below. All the intermediate and non-optimal values are omitted.

Face detections are performed using FaceDetV3 NN.

Jetson#

 

Jetson does not use mobilenet by default.

Performance measurements are presented for Jetson. Measured values are averages of at least 100 experiments. Mobilenet is not used by default.

Jetson TX#

Jetson TX GPU. Detector performance#

The table below shows the performance of Detector on the Jetson TX GPU.

Type Batch Size Average (ms)
Detector (minFaceSize=20) 1 333.73
Detector (minFaceSize=20) 4 415.49
Detector (minFaceSize=50) 1 63.49
Detector (minFaceSize=50) 4 57.71
Detector (minFaceSize=50) 8 57.25
Detector (minFaceSize=90) 1 27.5
Detector (minFaceSize=90) 4 23.11
Detector (minFaceSize=90) 8 22.34
Redetect 1 6.19
Redetect 4 3.52
Redetect 8 3.38
Redetect 16 3.26
FaceLandmarks5Detector 1 6.3
FaceLandmarks5Detector 8 0.8
FaceLandmarks5Detector 16 0.5
FaceLandmarks68Detector 1 6.3
FaceLandmarks68Detector 8 1.7
FaceLandmarks68Detector 16 1.2

Jetson TX GPU. HumanDetector performance#

The table below shows the performance of HumanDetector on the Jetson TX GPU.

Type Batch Size Average (ms)
HumanDetector (imageSize=320) 1 43.94
HumanDetector (imageSize=320) 4 40.04
HumanDetector (imageSize=320) 8 38.53
HumanDetector (imageSize=640) 1 43.61
HumanDetector (imageSize=640) 4 39.91
HumanDetector (imageSize=640) 8 38.46
HumanLandmarksDetector 1 51.9
HumanLandmarksDetector 4 20.0
HumanLandmarksDetector 8 17.8
HumanRedetect 1 6.15
HumanRedetect 4 4.09
HumanRedetect 8 3.5
HumanRedetect 16 3.41

Jetson TX GPU. HeadDetector performance#

The table below shows the performance of HeadDetector on the Jetson TX GPU.

Type Batch Size Average (ms)
HeadDetector (minHeadSize=20) 1 330.71
HeadDetector (minHeadSize=20) 4 404.94
HeadDetector (minHeadSize=20) 8 493.58
HeadDetector (minHeadSize=50) 1 61.17
HeadDetector (minHeadSize=50) 4 57.06
HeadDetector (minHeadSize=50) 8 56.85
HeadDetector (minHeadSize=90) 1 25.02
HeadDetector (minHeadSize=90) 4 22.2
HeadDetector (minHeadSize=90) 8 21.86

Jetson TX GPU. HumanFaceDetector performance#

The table below shows the performance of HumanFaceDetector on the Jetson TX GPU.

Type Batch Size Average (ms)
HumanFaceDetector (minFaceSize=20) 1 409.59
HumanFaceDetector (minFaceSize=50) 1 79.89
HumanFaceDetector (minFaceSize=50) 4 70.5
HumanFaceDetector (minFaceSize=50) 8 69.27
HumanFaceDetector (minFaceSize=90) 1 31.13
HumanFaceDetector (minFaceSize=90) 4 28.66
HumanFaceDetector (minFaceSize=90) 8 27.18

Jetson TX GPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the Jetson TX GPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
HeadPoseByImage 1 8.85
HeadPoseByImage 32 2.82
Eyes (INFRA_RED, useStatusPlan=0) 1 1.53
Eyes (INFRA_RED, useStatusPlan=0) 16 1.02
Eyes (INFRA_RED, useStatusPlan=0) 32 0.93
Eyes (RGB, useStatusPlan=0) 1 2.83
Eyes (RGB, useStatusPlan=0) 16 1.68
Eyes (RGB, useStatusPlan=0) 32 1.65
Eyes (INFRA_RED, useStatusPlan=1) 1 1.49
Eyes (INFRA_RED, useStatusPlan=1) 16 1.17
Eyes (INFRA_RED, useStatusPlan=1) 32 1.1
Eyes (RGB, useStatusPlan=1) 1 2.82
Eyes (RGB, useStatusPlan=1) 16 1.68
Eyes (RGB, useStatusPlan=1) 32 1.6
Infra-Red 1 3.29
AGS 1 5.02
AGS 16 2.57
Child 1 15.23
Child 16 8.95
BlackWhite 1 3.0
BlackWhite 16 1.1
BestShotQuality 1 5.41
BestShotQuality 16 2.59
MedicalMask 1 13.4
MedicalMask 32 4.98
LivenessOneShotRGBEstimator 1 221.9
LivenessOneShotRGBEstimator 8 202.94
LivenessOneShotRGBEstimator 16 202.78
Orientation 1 9.98
Orientation 16 8.3
Orientation 32 8.19
CredibilityCheck 1 44.5
CredibilityCheck 8 35.7
CredibilityCheck 16 34.4
CredibilityCheck 32 34.1
FacialHair 1 10.6
FacialHair 16 8.9
FacialHair 32 8.76
PortraitStyle 1 6.69
PortraitStyle 16 3.85
PortraitStyle 32 3.8
Background 1 7.2
Background 16 3.9
NaturalLight 1 13.8
NaturalLight 16 1.5
FishEye 1 10.7
FishEye 16 0.7
RedEye 1 2.1
RedEye 16 0.8
HeadWear 1 14.01
HeadWear 16 2.22
HeadWear 32 2.15
EyeBrowEstimator 1 10.56
EyeBrowEstimator 16 8.87
EyeBrowEstimator 32 8.76
HumanAttributeEstimator 1 20.78
HumanAttributeEstimator 16 4.93
Mouth 1 14.76
Mouth 16 4.14
Mouth 32 4.0

Jetson TX. Estimations performance for CPU based algorithms#

The table below shows the performance of Estimations on the Jetson Jetson TX for estimators with cpu based algorithms. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
DynamicRange 1 1.01
DynamicRange 16 0.45
DynamicRange 32 0.4

Jetson TX GPU. Estimations performance without batch interface#

The table below shows the performance of Estimations on the Jetson TX GPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Type Average (ms)
EyesGaze 4.29
Emotions 11.96
Attributes 27.24
Quality 2.17
Warper 8.08
Overlap 3.98
Glasses 3.63
PPE 22.41
LivenessFlyingFaces 18.76
LivenessRGBMEstimator 64.42
LivenessFPR 62.67

Jetson TX GPU. Extractor performance#

The table below shows the performance of Extractor on the Jetson TX GPU.

Model Batch Size Average (ms)
57 1 76.07
57 8 62.03
58 1 76.15
58 8 61.63
59 1 76.15
59 8 61.64
60 1 75.0
60 8 61.0
102 1 17.31
102 8 2.61
103 1 45.64
103 8 32.34
104 1 15.23
104 8 5.41
105 1 16.39
105 8 2.41
106 1 44.83
106 8 32.2
107 1 14.4
107 8 5.43

Jetson Xavier#

Jetson Xavier GPU. Detector performance#

The table below shows the performance of Detector on the Jetson Xavier GPU.

Type Batch Size Average (ms)
Detector (minFaceSize=20) 1 145.24
Detector (minFaceSize=20) 4 202.78
Detector (minFaceSize=20) 8 260.95
Detector (minFaceSize=50) 1 30.65
Detector (minFaceSize=50) 4 27.8
Detector (minFaceSize=50) 8 26.82
Detector (minFaceSize=90) 1 15.36
Detector (minFaceSize=90) 4 11.71
Detector (minFaceSize=90) 8 10.78
Redetect 1 3.35
Redetect 4 1.84
Redetect 8 1.51
Redetect 16 1.36
FaceLandmarks5Detector 1 3.0
FaceLandmarks5Detector 8 0.6
FaceLandmarks5Detector 16 0.3
FaceLandmarks68Detector 1 4.5
FaceLandmarks68Detector 8 0.9
FaceLandmarks68Detector 16 0.7

Jetson Xavier GPU. HumanDetector performance#

The table below shows the performance of HumanDetector on the Jetson Xavier GPU.

Type Batch Size Average (ms)
HumanDetector (imageSize=320) 1 10.44
HumanDetector (imageSize=320) 4 7.34
HumanDetector (imageSize=320) 8 6.47
HumanDetector (imageSize=640) 1 21.32
HumanDetector (imageSize=640) 4 18.4
HumanDetector (imageSize=640) 8 17.55
HumanLandmarksDetector 1 29.2
HumanLandmarksDetector 4 14.4
HumanLandmarksDetector 8 11.7
HumanRedetect 1 3.83
HumanRedetect 4 1.98
HumanRedetect 8 1.71
HumanRedetect 16 1.48

Jetson Xavier GPU. HumanFaceDetector performance#

The table below shows the performance of HumanFaceDetector on the Jetson Xavier GPU.

Type Batch Size Average (ms)
HumanFaceDetector (minFaceSize=20) 1 174.06
HumanFaceDetector (minFaceSize=20) 4 279.21
HumanFaceDetector (minFaceSize=20) 8 342.85
HumanFaceDetector (minFaceSize=50) 1 36.6
HumanFaceDetector (minFaceSize=50) 4 32.84
HumanFaceDetector (minFaceSize=50) 8 31.67
HumanFaceDetector (minFaceSize=90) 1 18.45
HumanFaceDetector (minFaceSize=90) 4 13.64
HumanFaceDetector (minFaceSize=90) 8 12.53

Jetson Xavier GPU. HeadDetector performance#

The table below shows the performance of HeadDetector on the Jetson Xavier GPU.

Type Batch Size Average (ms)
HeadDetector (minHeadSize=20) 1 144.01
HeadDetector (minHeadSize=20) 4 203.21
HeadDetector (minHeadSize=20) 8 265.55
HeadDetector (minHeadSize=50) 1 29.46
HeadDetector (minHeadSize=50) 4 27.28
HeadDetector (minHeadSize=50) 8 26.56
HeadDetector (minHeadSize=90) 1 14.23
HeadDetector (minHeadSize=90) 4 11.31
HeadDetector (minHeadSize=90) 8 10.49

Jetson Xavier GPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the Jetson Xavier GPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
HeadPoseByImage 1 4.38
HeadPoseByImage 32 0.89
Eyes (INFRA_RED, useStatusPlan=0) 1 1.12
Eyes (INFRA_RED, useStatusPlan=0) 16 0.53
Eyes (INFRA_RED, useStatusPlan=0) 32 0.48
Eyes (RGB, useStatusPlan=0) 1 2.17
Eyes (RGB, useStatusPlan=0) 16 1.0
Eyes (RGB, useStatusPlan=0) 32 0.99
Eyes (INFRA_RED, useStatusPlan=1) 1 1.12
Eyes (INFRA_RED, useStatusPlan=1) 16 0.51
Eyes (INFRA_RED, useStatusPlan=1) 32 0.5
Eyes (RGB, useStatusPlan=1) 1 2.16
Eyes (RGB, useStatusPlan=1) 16 1.1
Eyes (RGB, useStatusPlan=1) 32 0.99
Infra-Red 1 2.3
Infra-Red 32 1.25
AGS 1 2.83
AGS 32 0.86
Child 1 8.37
Child 8 5.88
BlackWhite 1 2.2
BlackWhite 16 0.6
BestShotQuality 1 3.04
BestShotQuality 32 0.88
MedicalMask 1 6.59
MedicalMask 32 3.45
LivenessOneShotRGBEstimator 1 118.91
LivenessOneShotRGBEstimator 8 98.02
LivenessOneShotRGBEstimator 16 97.22
Orientation 1 5.43
Orientation 16 3.69
Orientation 32 3.59
CredibilityCheck 1 35.2
CredibilityCheck 8 25.09
CredibilityCheck 16 24.64
CredibilityCheck 32 24.22
FacialHair 1 7.18
FacialHair 16 4.95
FacialHair 32 4.86
PortraitStyle 1 3.58
PortraitStyle 16 1.84
PortraitStyle 32 1.79
Background 1 3.8
Background 16 1.8
NaturalLight 1 3.6
NaturalLight 16 1.5
FishEye 1 7.0
FishEye 16 0.4
RedEye 1 2.0
RedEye 16 0.5
HeadWear 1 6.3
HeadWear 16 2.39
HeadWear 32 2.21
EyeBrowEstimator 1 6.97
EyeBrowEstimator 16 4.96
EyeBrowEstimator 32 4.86
HumanAttributeEstimator 1 10.73
HumanAttributeEstimator 16 4.03
Mouth 1 5.84
Mouth 16 2.63
Mouth 32 2.33

Jetson Xavier. Estimations performance for CPU based algorithms#

The table below shows the performance of Estimations on the Jetson Xavier for estimators with CPU based algorithms. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
DynamicRange 1 0.7
DynamicRange 16 0.27
DynamicRange 32 0.24

Jetson Xavier GPU. Estimations performance without batch interface#

The table below shows the performance of Estimations on the Jetson Xavier GPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Type Average (ms)
EyesGaze 2.99
Emotions 7.48
Attributes 20.3
Quality 1.64
Warper 6.63
Overlap 3.03
PPE 8.28
Glasses 2.14
LivenessFlyingFaces 8.84
LivenessRGBMEstimator 27.14
LivenessFPR 39.41

Jetson Xavier GPU. Extractor performance#

The table below shows the performance of Extractor on the Jetson Xavier GPU.

Model Batch Size Average (ms)
57 1 66.4
57 8 44.1
58 1 66.2
58 8 44.1
59 1 66.3
59 8 44.1
60 1 66.0
60 8 44.0
102 1 8.3
102 8 0.98
103 1 18.3
103 8 19.4
104 1 6.6
104 8 2.4
105 1 8.68
105 8 1.7
106 1 32.58
106 8 33.87
107 1 8.19
107 8 4.44

Jetson Xavier NX#

Jetson Xavier NX GPU. Detector performance#

The table below shows the performance of Detector on the Jetson Xavier NX GPU.

Type Batch Size Average (ms)
Detector (minFaceSize=20) 1 143.5
Detector (minFaceSize=20) 4 213.2
Detector (minFaceSize=20) 8 30.6
Detector (minFaceSize=50) 1 27.88
Detector (minFaceSize=50) 4 26.97
Detector (minFaceSize=50) 8 14.96
Detector (minFaceSize=90) 1 11.5
Detector (minFaceSize=90) 4 10.65
Detector (minFaceSize=90) 8 4.05
Redetect 1 1.97
Redetect 4 1.69
Redetect 8 1.48
FaceLandmarks5Detector 1 2.5
FaceLandmarks5Detector 8 1.0
FaceLandmarks5Detector 16 0.8
FaceLandmarks68Detector 1 4.9
FaceLandmarks68Detector 8 2.0
FaceLandmarks68Detector 16 1.8

Jetson Xavier NX GPU. HumanDetector performance#

The table below shows the performance of HumanDetector on the Jetson Xavier NX GPU.

Type Batch Size Average (ms)
HumanDetector (imageSize=320) 1 19.95
HumanDetector (imageSize=320) 4 18.21
HumanDetector (imageSize=320) 8 17.5
HumanDetector (imageSize=640) 1 19.79
HumanDetector (imageSize=640) 4 18.33
HumanDetector (imageSize=640) 8 17.59
HumanLandmarksDetector 1 33.6
HumanLandmarksDetector 4 12.7
HumanLandmarksDetector 8 10.9
HumanRedetect 1 4.1
HumanRedetect 4 2.07
HumanRedetect 8 1.74
HumanRedetect 16 1.57
HumanDetector (imageSize=640) 1 28.2
HumanDetector (imageSize=640) 16 30.2
HumanDetector (imageSize=640) 32 35.5

Jetson Xavier NX GPU. HeadDetector performance#

The table below shows the performance of HeadDetector on the Jetson Xavier NX GPU.

Type Batch Size Average (ms)
HeadDetector (minHeadSize=20) 1 141.38
HeadDetector (minHeadSize=20) 4 185.18
HeadDetector (minHeadSize=50) 1 28.37
HeadDetector (minHeadSize=50) 4 27.83
HeadDetector (minHeadSize=50) 8 26.8
HeadDetector (minHeadSize=90) 1 12.97
HeadDetector (minHeadSize=90) 4 11.04
HeadDetector (minHeadSize=90) 8 10.41

Jetson Xavier NX GPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the Jetson Xavier NX GPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
HeadPoseByImage 1 5.6
HeadPoseByImage 32 1.3
Eyes (INFRA_RED, useStatusPlan=0) 1 1.36
Eyes (INFRA_RED, useStatusPlan=0) 16 0.65
Eyes (INFRA_RED, useStatusPlan=0) 32 0.6
Eyes (RGB, useStatusPlan=0) 1 2.21
Eyes (RGB, useStatusPlan=0) 16 1.09
Eyes (RGB, useStatusPlan=0) 32 1.01
Eyes (INFRA_RED, useStatusPlan=1) 1 1.37
Eyes (INFRA_RED, useStatusPlan=1) 16 0.71
Eyes (INFRA_RED, useStatusPlan=1) 32 0.65
Eyes (RGB, useStatusPlan=1) 1 2.48
Eyes (RGB, useStatusPlan=1) 16 1.31
Eyes (RGB, useStatusPlan=1) 32 1.21
Infra-Red 1 2.32
Infra-Red 32 1.49
AGS 1 3.41
AGS 32 1.25
Child 1 7.85
Child 8 5.49
BlackWhite 1 2.4
BlackWhite 16 0.7
BestShotQuality 1 3.59
BestShotQuality 32 1.27
MedicalMask 1 7.01
MedicalMask 32 3.41
LivenessOneShotRGBEstimator 1 146.14
LivenessOneShotRGBEstimator 8 100.95
LivenessOneShotRGBEstimator 16 99.96
Orientation 1 5.21
Orientation 16 3.75
Orientation 32 3.66
CredibilityCheck 1 31.05
CredibilityCheck 8 22.59
CredibilityCheck 16 21.91
CredibilityCheck 32 21.5
FacialHair 1 6.53
FacialHair 16 4.73
FacialHair 32 4.62
PortraitStyle 1 4.42
PortraitStyle 16 1.92
PortraitStyle 32 1.86
Background 1 4.0
Background 16 2.1
NaturalLight 1 4.48
NaturalLight 16 1.26
FishEye 1 6.5
FishEye 16 0.4
RedEye 1 2.1
RedEye 16 0.5
HeadWear 1 4.57
HeadWear 16 1.27
HeadWear 32 1.18
EyeBrowEstimator 1 6.54
EyeBrowEstimator 16 4.77
EyeBrowEstimator 32 4.69
HumanAttributeEstimator 1 11.71
HumanAttributeEstimator 16 3.63
Mouth 1 6.91
Mouth 16 2.36
Mouth 32 2.14

Jetson Xavier NX. Estimations performance for CPU based algorithms#

The table below shows the performance of Estimations on the Jetson Xavier NX for estimators with cpu based algorithms. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
DynamicRange 1 1.05
DynamicRange 16 0.38
DynamicRange 32 0.36

Jetson Xavier NX GPU. Estimations performance without batch interface#

The table below shows the performance of Estimations on the Jetson Xavier NX GPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Type Average (ms)
EyesGaze 3.7
Emotions 6.8
Attributes 17.36
Quality 1.59
Warper 9.82
Overlap 3.56
PPE 8.79
Glasses 2.05
LivenessFlyingFaces 9.63
LivenessRGBMEstimator 28.1
LivenessFPR 40.5

Jetson Xavier NX GPU. Extractor performance#

The table below shows the performance of Extractor on the Jetson Xavier NX GPU.

Model Batch Size Average (ms)
57 1 58.2
57 16 38.1
58 1 58.0
58 16 38.1
59 1 58.0
59 16 38.0
60 1 58.0
60 16 39.0
102 1 10.7
102 16 1.0
103 1 28.4
103 16 41.3
104 1 9.8
104 16 3.6
105 1 12.7
105 16 1.8
106 1 20.3
106 16 35.3
107 1 8.1
107 16 3.0

Jetson Nano#

Jetson Nano GPU. Detector performance#

The table below shows the performance of Detector on the Jetson Nano GPU.

Type Batch Size Average (ms)
Detector (minFaceSize=20) 1 1594.53
Detector (minFaceSize=50) 1 304.12
Detector (minFaceSize=50) 4 308.74
Detector (minFaceSize=50) 8 313.25
Detector (minFaceSize=90) 1 127.69
Detector (minFaceSize=90) 4 116.31
Detector (minFaceSize=90) 8 117.14
Redetect 1 11.08
Redetect 8 6.78
Redetect 16 6.8
FaceLandmarks5Detector 1 7.0
FaceLandmarks5Detector 8 3.0
FaceLandmarks5Detector 16 2.0
FaceLandmarks68Detector 1 12.0
FaceLandmarks68Detector 8 6.0
FaceLandmarks68Detector 16 5.7

Jetson Nano GPU. HumanDetector performance#

The table below shows the performance of HumanDetector on the Jetson Nano GPU.

Type Batch Size Average (ms)
HumanDetector (imageSize=320) 1 99.39
HumanDetector (imageSize=320) 4 95.06
HumanDetector (imageSize=320) 8 93.46
HumanDetector (imageSize=640) 1 99.05
HumanDetector (imageSize=640) 4 94.89
HumanDetector (imageSize=640) 8 92.83
HumanLandmarksDetector 1 140.5
HumanLandmarksDetector 4 103.2
HumanLandmarksDetector 8 98.0
HumanRedetect 1 10.69
HumanRedetect 4 8.14
HumanRedetect 8 7.25
HumanRedetect 16 7.61

Jetson Nano GPU. HeadDetector performance#

The table below shows the performance of HeadDetector on the Jetson Nano GPU.

Type Batch Size Average (ms)
HeadDetector (minHeadSize=20) 1 807.96
HeadDetector (minHeadSize=50) 1 144.36
HeadDetector (minHeadSize=50) 4 142.21
HeadDetector (minHeadSize=50) 8 141.49
HeadDetector (minHeadSize=90) 1 55.65
HeadDetector (minHeadSize=90) 4 52.83
HeadDetector (minHeadSize=90) 8 52.22

Jetson Nano GPU. HumanFaceDetector performance#

The table below shows the performance of HumanFaceDetector on the Jetson Nano GPU.

Type Batch Size Average (ms)
HumanFaceDetector (minFaceSize=20) 1 977.41
HumanFaceDetector (minFaceSize=50) 1 181.66
HumanFaceDetector (minFaceSize=50) 4 171.81
HumanFaceDetector (minFaceSize=50) 8 169.98
HumanFaceDetector (minFaceSize=90) 1 70.55
HumanFaceDetector (minFaceSize=90) 4 65.34
HumanFaceDetector (minFaceSize=90) 8 63.85

Jetson Nano GPU. Estimations performance with batch interface#

The table below shows the performance of Estimations on the Jetson Nano GPU for estimators that have a batch interface. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
HeadPoseByImage 1 6.59
HeadPoseByImage 4 5.2
HeadPoseByImage 16 3.49
Warper 1 1.8
Warper 4 1.62
Warper 16 1.68
Eyes (INFRA_RED, useStatusPlan=0) 1 3.5
Eyes (INFRA_RED, useStatusPlan=0) 4 2.93
Eyes (INFRA_RED, useStatusPlan=0) 16 2.71
Eyes (RGB, useStatusPlan=0) 1 6.9
Eyes (RGB, useStatusPlan=0) 4 5.82
Eyes (RGB, useStatusPlan=0) 16 5.23
Eyes (INFRA_RED, useStatusPlan=1) 1 3.51
Eyes (INFRA_RED, useStatusPlan=1) 4 2.88
Eyes (INFRA_RED, useStatusPlan=1) 16 2.63
Eyes (RGB, useStatusPlan=1) 1 7.44
Eyes (RGB, useStatusPlan=1) 4 5.77
Eyes (RGB, useStatusPlan=1) 16 5.33
Infra-Red 1 9.76
Infra-Red 4 8.62
Infra-Red 16 8.32
AGS 1 6.26
AGS 4 4.19
AGS 16 3.5
Child 1 63.82
Child 4 48.97
Child 16 42.4
BlackWhite 1 6.17
BlackWhite 4 3.41
BlackWhite 16 2.76
BestShotQuality 1 6.68
BestShotQuality 4 4.43
BestShotQuality 16 3.53
MedicalMask 1 26.13
MedicalMask 4 19.52
MedicalMask 16 17.62
LivenessOneShotRGBEstimator 1 518.35
LivenessOneShotRGBEstimator 4 505.36
Orientation 1 19.93
Orientation 4 18.15
Orientation 16 17.6
CredibilityCheck 1 282.77
CredibilityCheck 4 250.91
CredibilityCheck 16 240.66
FacialHair 1 23.97
FacialHair 4 23.43
FacialHair 16 23.0
PortraitStyle 1 8.41
PortraitStyle 4 6.35
PortraitStyle 16 6.04
Background 1 12.8
Background 4 10.82
Background 16 9.98
NaturalLight 1 27.08
NaturalLight 4 10.89
NaturalLight 16 7.43
FishEye 1 24.5
FishEye 4 6.0
FishEye 16 1.0
RedEye 1 7.9
RedEye 4 5.2
RedEye 16 4.63
HeadWear 1 26.33
HeadWear 4 6.62
HeadWear 16 5.36
EyeBrowEstimator 1 23.8
EyeBrowEstimator 4 23.33
EyeBrowEstimator 16 22.98
HumanAttributeEstimator 1 33.19
HumanAttributeEstimator 8 15.07
HumanAttributeEstimator 16 13.04
Mouth 1 41.05
Mouth 4 35.52
Mouth 16 24.92

Jetson Nano. Estimations performance for CPU based algorithms#

The table below shows the performance of Estimations on the Jetson Nano for estimators with only CPU based algorithms. All these measurements are performed with minFaceSize=50.

Type Batch Size Average (ms)
DynamicRange 1 1.25
DynamicRange 4 0.74
DynamicRange 16 0.61

Jetson Nano GPU. Estimation performance without batch interface#

The table below shows the performance of Estimations on the Jetson Nano GPU for estimators that do not have a batch interface. All these measurements are performed with minFaceSize=50.

Type Average (ms)
EyesGaze 12.37
Emotions 49.04
Attributes 140.48
Quality 4.35
Overlap 10.28
PPE 32.25
Glasses 10.83
LivenessFlyingFaces 23.64
LivenessRGBMEstimator 172.06
LivenessFPR 206.17

Jetson Nano GPU. Extractor performance#

The table below shows the performance of Extractor on the Jetson Nano GPU.

Model Batch Size Average (ms)
58 1 442.35
58 4 403.95
59 1 428.35
59 4 411.47
60 1 176.3
60 4 163.4
102 1 26.17
102 4 9.9
103 1 254.11
103 4 215.07
104 1 39.97
104 4 31.63
105 1 20.65
105 4 9.9
106 1 296.11
106 4 245.15
107 1 32.92
107 4 35.55

Descriptor size#

Table below shows size of serialized face descriptors to estimate memory requirements.

"Descriptor size"

Face descriptor version Data size (bytes) Metadata size (bytes) Total size
CNN 54 512 8 520
CNN 56 512 8 520
CNN 57 512 8 520
CNN 58 512 8 520
CNN 59 512 8 520

Table below shows size of serialized human descriptors to estimate memory requirements. Human descriptors are used only for reidentification tasks.

"Human descriptor size (used only for reidentification tasks)"

Human descriptor version Data size (bytes) Metadata size (bytes) Total size
CNN 102 2048 8 2056
CNN 103 2048 8 2056
CNN 104 2048 8 2056
CNN 105 512 8 520
CNN 106 512 8 520
CNN 107 512 8 520

Metadata includes signature and version information that may be omitted during serialization if the NoSignature flag is specified.

When estimating individual descriptor size in memory or serialization storage requirements with default options, consider using values from the "Total size" column.

When estimating memory requirements for descriptor batches, use values from the "Data size" column instead, since a descriptor batch does not duplicate metadata per descriptor and thus is more memory-efficient.

These numbers are for approximate computation only, since they do not include overhead like memory alignment for accelerated SIMD processing and the like.