Geekbench ML Score

44
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.2 for Android AArch64

Result Information

Upload Date September 21 2024 11:06 PM
Views 2

System Information

System Information
Operating System Android 10
Model motorola moto g(8) power lite
Model IDmotorola moto g(8) power lite
Motherboard blackjack
CPU Information
Name ARM MT6765V/WB
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 3.68 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 27
2.89 IPS
 
Image Classification (F16)
100% 26
2.81 IPS
 
Image Classification (I8)
81% 67
7.18 IPS
 
Image Segmentation (F32)
100% 52
0.32 IPS
 
Image Segmentation (F16)
100% 55
0.34 IPS
 
Image Segmentation (I8)
89% 121
0.75 IPS
 
Pose Estimation (F32)
100% 37
0.15 IPS
 
Pose Estimation (F16)
100% 37
0.15 IPS
 
Pose Estimation (I8)
80% 20
0.08 IPS
 
Object Detection (F32)
100% 42
1.47 IPS
 
Object Detection (F16)
100% 38
1.35 IPS
 
Object Detection (I8)
52% 96
3.37 IPS
 
Face Detection (F32)
100% 48
0.55 IPS
 
Face Detection (F16)
100% 48
0.55 IPS
 
Face Detection (I8)
75% 97
1.11 IPS
 
Text Classification (F32)
100% 81
31.8 IPS
 
Text Classification (F16)
100% 78
30.9 IPS
 
Machine Translation (F32)
100% 13
2.05 IPS
 
Machine Translation (F16)
100% 14
2.16 IPS
 

Compare

Set Baseline Geekbench 6 now available