Geekbench ML Score

156
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2023 03:13 PM
Views 46

System Information

System Information
Operating System Android 12
Model ZTE ZTE A7050
Model IDZTE ZTE A7050
Motherboard ums9230_4h10
Governorschedutil
CPU Information
Name ARM Unisoc
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.61 GHz
Cluster 18 Cores @ 1.61 GHz
Memory Information
Size 2.52 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 96
10.3 IPS
 
Image Classification (F16)
100% 97
10.4 IPS
 
Image Classification (I8)
81% 218
23.3 IPS
 
Image Segmentation (F32)
100% 215
1.33 IPS
 
Image Segmentation (F16)
100% 220
1.36 IPS
 
Image Segmentation (I8)
89% 502
3.10 IPS
 
Pose Estimation (F32)
100% 74
0.30 IPS
 
Pose Estimation (F16)
100% 70
0.28 IPS
 
Pose Estimation (I8)
80% 110
0.44 IPS
 
Object Detection (F32)
100% 147
5.18 IPS
 
Object Detection (F16)
100% 150
5.28 IPS
 
Object Detection (I8)
52% 255
8.93 IPS
 
Face Detection (F32)
100% 204
2.35 IPS
 
Face Detection (F16)
100% 198
2.27 IPS
 
Face Detection (I8)
75% 359
4.12 IPS
 
Text Classification (F32)
100% 136
53.6 IPS
 
Text Classification (F16)
100% 136
53.9 IPS
 
Machine Translation (F32)
100% 108
16.7 IPS
 
Machine Translation (F16)
100% 108
16.6 IPS
 

Compare

Set Baseline Geekbench 6 now available