Geekbench ML Score

82
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 31 2023 01:48 AM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-S215DL
Model IDsamsung SM-S215DL
Motherboard a21
CPU Information
Name ARM MT6765V/CA
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3331 revision 4
Base Frequency 2.30 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.30 GHz
Memory Information
Size 2.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 43
4.58 IPS
 
Image Classification (F16)
100% 47
5.03 IPS
 
Image Classification (I8)
81% 201
21.5 IPS
 
Image Segmentation (F32)
100% 110
0.68 IPS
 
Image Segmentation (F16)
100% 112
0.69 IPS
 
Image Segmentation (I8)
89% 360
2.23 IPS
 
Pose Estimation (F32)
100% 61
0.25 IPS
 
Pose Estimation (F16)
100% 58
0.23 IPS
 
Pose Estimation (I8)
80% 105
0.42 IPS
 
Object Detection (F32)
100% 72
2.52 IPS
 
Object Detection (F16)
100% 86
3.01 IPS
 
Object Detection (I8)
52% 234
8.21 IPS
 
Face Detection (F32)
100% 108
1.24 IPS
 
Face Detection (F16)
100% 102
1.17 IPS
 
Face Detection (I8)
75% 321
3.69 IPS
 
Text Classification (F32)
100% 67
26.5 IPS
 
Text Classification (F16)
100% 73
29.1 IPS
 
Machine Translation (F32)
100% 13
1.94 IPS
 
Machine Translation (F16)
100% 12
1.78 IPS
 

Compare

Set Baseline Geekbench 6 now available