Geekbench ML Score

644
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 22 2023 09:16 AM
Views 6

System Information

System Information
Operating System Android 13
Model samsung SM-S918B
Model IDsamsung SM-S918B
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 10.80 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 561
60.1 IPS
 
Image Classification (F16)
100% 438
47.0 IPS
 
Image Classification (I8)
81% 514
55.1 IPS
 
Image Segmentation (F32)
100% 843
5.21 IPS
 
Image Segmentation (F16)
100% 848
5.23 IPS
 
Image Segmentation (I8)
89% 894
5.52 IPS
 
Pose Estimation (F32)
100% 328
1.33 IPS
 
Pose Estimation (F16)
100% 321
1.30 IPS
 
Pose Estimation (I8)
80% 150
0.61 IPS
 
Object Detection (F32)
100% 613
21.5 IPS
 
Object Detection (F16)
100% 603
21.2 IPS
 
Object Detection (I8)
52% 591
20.7 IPS
 
Face Detection (F32)
100% 820
9.42 IPS
 
Face Detection (F16)
100% 824
9.47 IPS
 
Face Detection (I8)
75% 682
7.83 IPS
 
Text Classification (F32)
100% 1192
471.4 IPS
 
Text Classification (F16)
100% 1234
488.2 IPS
 
Machine Translation (F32)
100% 1133
174.6 IPS
 
Machine Translation (F16)
100% 1100
169.5 IPS
 

Compare

Set Baseline Geekbench 6 now available