Geekbench ML Score

144
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 09:56 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-N975F
Model IDsamsung SM-N975F
Motherboard exynos9825
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 @ 2.40 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 11.15 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 74
7.91 IPS
 
Image Classification (F16)
100% 72
7.68 IPS
 
Image Classification (I8)
81% 98
10.5 IPS
 
Image Segmentation (F32)
100% 185
1.14 IPS
 
Image Segmentation (F16)
100% 182
1.12 IPS
 
Image Segmentation (I8)
89% 379
2.34 IPS
 
Pose Estimation (F32)
100% 114
0.46 IPS
 
Pose Estimation (F16)
100% 112
0.45 IPS
 
Pose Estimation (I8)
80% 111
0.45 IPS
 
Object Detection (F32)
100% 103
3.61 IPS
 
Object Detection (F16)
100% 120
4.22 IPS
 
Object Detection (I8)
52% 131
4.60 IPS
 
Face Detection (F32)
100% 180
2.07 IPS
 
Face Detection (F16)
100% 175
2.01 IPS
 
Face Detection (I8)
75% 229
2.63 IPS
 
Text Classification (F32)
100% 115
45.5 IPS
 
Text Classification (F16)
100% 110
43.6 IPS
 
Machine Translation (F32)
100% 274
42.2 IPS
 
Machine Translation (F16)
100% 291
44.8 IPS
 

Compare

Set Baseline