Geekbench ML Score

3134
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 02:33 AM
Views 4

System Information

System Information
Operating System Android 12
Model samsung SM-X706N
Model IDsamsung SM-X706N
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1328
142.3 IPS
 
Image Classification (F16)
100% 8915
955.2 IPS
 
Image Classification (I8)
80% 20609
2.21 KIPS
 
Image Segmentation (F32)
100% 2831
17.5 IPS
 
Image Segmentation (F16)
100% 8271
51.1 IPS
 
Image Segmentation (I8)
89% 41197
254.5 IPS
 
Pose Estimation (F32)
100% 601
2.43 IPS
 
Pose Estimation (F16)
100% 10450
42.3 IPS
 
Pose Estimation (I8)
80% 54592
220.9 IPS
 
Object Detection (F32)
100% 1035
36.3 IPS
 
Object Detection (F16)
100% 1800
63.2 IPS
 
Object Detection (I8)
53% 1996
70.0 IPS
 
Face Detection (F32)
100% 1996
22.9 IPS
 
Face Detection (F16)
97% 7136
82.0 IPS
 
Face Detection (I8)
76% 47448
545.1 IPS
 
Text Classification (F32)
100% 17
6.70 IPS
 
Text Classification (F16)
100% 801
317.0 IPS
 
Machine Translation (F32)
100% 991
152.7 IPS
 
Machine Translation (F16)
100% 979
150.9 IPS
 

Compare

Set Baseline