Geekbench ML Score

162
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 22 2023 12:17 PM
Views 1

System Information

System Information
Operating System Android 11
Model HMD Global Nokia G11
Model IDHMD Global Nokia G11
Motherboard Shadowcat
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 2.48 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 106
11.4 IPS
 
Image Classification (F16)
100% 106
11.4 IPS
 
Image Classification (I8)
81% 198
21.3 IPS
 
Image Segmentation (F32)
100% 218
1.35 IPS
 
Image Segmentation (F16)
100% 218
1.34 IPS
 
Image Segmentation (I8)
89% 498
3.07 IPS
 
Pose Estimation (F32)
100% 92
0.37 IPS
 
Pose Estimation (F16)
100% 90
0.37 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 149
5.24 IPS
 
Object Detection (F16)
100% 148
5.21 IPS
 
Object Detection (I8)
52% 255
8.96 IPS
 
Face Detection (F32)
100% 205
2.36 IPS
 
Face Detection (F16)
100% 207
2.38 IPS
 
Face Detection (I8)
75% 364
4.18 IPS
 
Text Classification (F32)
100% 134
52.8 IPS
 
Text Classification (F16)
100% 134
52.9 IPS
 
Machine Translation (F32)
100% 107
16.4 IPS
 
Machine Translation (F16)
100% 107
16.4 IPS
 

Compare

Set Baseline Geekbench 6 now available