Geekbench ML Score

228
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 08:54 AM
Views 2

System Information

System Information
Operating System Android 12
Model samsung SM-G970N
Model IDsamsung SM-G970N
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 5.29 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 148
15.9 IPS
 
Image Classification (F16)
100% 101
10.9 IPS
 
Image Classification (I8)
81% 153
16.4 IPS
 
Image Segmentation (F32)
100% 310
1.91 IPS
 
Image Segmentation (F16)
100% 334
2.06 IPS
 
Image Segmentation (I8)
89% 605
3.74 IPS
 
Pose Estimation (F32)
100% 156
0.63 IPS
 
Pose Estimation (F16)
100% 151
0.61 IPS
 
Pose Estimation (I8)
80% 181
0.73 IPS
 
Object Detection (F32)
100% 136
4.77 IPS
 
Object Detection (F16)
100% 141
4.93 IPS
 
Object Detection (I8)
52% 222
7.78 IPS
 
Face Detection (F32)
100% 253
2.91 IPS
 
Face Detection (F16)
100% 242
2.78 IPS
 
Face Detection (I8)
75% 390
4.48 IPS
 
Text Classification (F32)
100% 191
75.6 IPS
 
Text Classification (F16)
100% 203
80.1 IPS
 
Machine Translation (F32)
100% 528
81.3 IPS
 
Machine Translation (F16)
100% 521
80.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download