Geekbench ML Score

133
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 09:35 AM
Views 1

System Information

System Information
Operating System Android 11
Model Samsung Galaxy A50s
Model IDsamsung SM-A507FN
Motherboard exynos9611
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 5.47 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 73
7.79 IPS
 
Image Classification (F16)
100% 72
7.70 IPS
 
Image Classification (I8)
81% 113
12.1 IPS
 
Image Segmentation (F32)
100% 203
1.25 IPS
 
Image Segmentation (F16)
100% 199
1.23 IPS
 
Image Segmentation (I8)
89% 437
2.70 IPS
 
Pose Estimation (F32)
100% 75
0.31 IPS
 
Pose Estimation (F16)
100% 76
0.31 IPS
 
Pose Estimation (I8)
80% 132
0.53 IPS
 
Object Detection (F32)
100% 114
4.00 IPS
 
Object Detection (F16)
100% 125
4.38 IPS
 
Object Detection (I8)
52% 176
6.18 IPS
 
Face Detection (F32)
100% 177
2.03 IPS
 
Face Detection (F16)
100% 162
1.86 IPS
 
Face Detection (I8)
75% 267
3.07 IPS
 
Text Classification (F32)
100% 124
49.1 IPS
 
Text Classification (F16)
100% 124
48.9 IPS
 
Machine Translation (F32)
100% 104
16.1 IPS
 
Machine Translation (F16)
100% 98
15.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download