Geekbench ML Score

129
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 01:17 PM
Views 1

System Information

System Information
Operating System Android 11
Model Samsung Galaxy A50
Model IDsamsung SM-A505FN
Motherboard exynos9610
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 0 part 3337 revision 2
Base Frequency 1.74 GHz
Cluster 14 Cores @ 1.74 GHz
Cluster 24 Cores @ 2.31 GHz
Memory Information
Size 3.52 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 69
7.43 IPS
 
Image Classification (F16)
100% 64
6.82 IPS
 
Image Classification (I8)
81% 107
11.5 IPS
 
Image Segmentation (F32)
100% 192
1.19 IPS
 
Image Segmentation (F16)
100% 195
1.20 IPS
 
Image Segmentation (I8)
89% 421
2.60 IPS
 
Pose Estimation (F32)
100% 72
0.29 IPS
 
Pose Estimation (F16)
100% 69
0.28 IPS
 
Pose Estimation (I8)
80% 123
0.50 IPS
 
Object Detection (F32)
100% 116
4.08 IPS
 
Object Detection (F16)
100% 113
3.96 IPS
 
Object Detection (I8)
52% 177
6.22 IPS
 
Face Detection (F32)
100% 171
1.96 IPS
 
Face Detection (F16)
100% 167
1.92 IPS
 
Face Detection (I8)
75% 260
2.99 IPS
 
Text Classification (F32)
100% 123
48.7 IPS
 
Text Classification (F16)
100% 124
49.2 IPS
 
Machine Translation (F32)
100% 106
16.3 IPS
 
Machine Translation (F16)
100% 105
16.1 IPS
 

Compare

Set Baseline