Geekbench ML Score

245
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 25 2023 09:37 AM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-G975F
Model IDsamsung SM-G975F
Motherboard exynos9820
Governorschedutil
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 3 revision 0
Base Frequency 1.95 GHz
Cluster 14 Cores @ 1.95 GHz
Cluster 22 Cores @ 2.31 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 7.25 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 149
15.9 IPS
 
Image Classification (F16)
100% 111
11.9 IPS
 
Image Classification (I8)
81% 152
16.2 IPS
 
Image Segmentation (F32)
100% 312
1.93 IPS
 
Image Segmentation (F16)
100% 336
2.07 IPS
 
Image Segmentation (I8)
89% 621
3.84 IPS
 
Pose Estimation (F32)
100% 172
0.70 IPS
 
Pose Estimation (F16)
100% 168
0.68 IPS
 
Pose Estimation (I8)
80% 193
0.78 IPS
 
Object Detection (F32)
100% 142
4.98 IPS
 
Object Detection (F16)
100% 139
4.89 IPS
 
Object Detection (I8)
52% 228
8.00 IPS
 
Face Detection (F32)
100% 304
3.49 IPS
 
Face Detection (F16)
100% 349
4.00 IPS
 
Face Detection (I8)
75% 389
4.47 IPS
 
Text Classification (F32)
100% 227
89.9 IPS
 
Text Classification (F16)
100% 198
78.4 IPS
 
Machine Translation (F32)
100% 584
90.0 IPS
 
Machine Translation (F16)
100% 575
88.7 IPS
 

Compare

Set Baseline Geekbench 6 now available