Geekbench ML Score

3177
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date April 21 2022 06:28 PM
Views 3

System Information

System Information
Operating System Android 12
Model motorola motorola edge 30 pro
Model IDmotorola motorola edge 30 pro
Motherboard hiphi
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 10.98 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1309
140.2 IPS
 
Image Classification (F16)
100% 9306
997.1 IPS
 
Image Classification (I8)
80% 23024
2.47 KIPS
 
Image Segmentation (F32)
100% 2847
17.6 IPS
 
Image Segmentation (F16)
100% 8365
51.7 IPS
 
Image Segmentation (I8)
89% 43540
268.9 IPS
 
Pose Estimation (F32)
100% 607
2.46 IPS
 
Pose Estimation (F16)
100% 10659
43.1 IPS
 
Pose Estimation (I8)
80% 55545
224.8 IPS
 
Object Detection (F32)
100% 1042
36.6 IPS
 
Object Detection (F16)
100% 1780
62.5 IPS
 
Object Detection (I8)
53% 1987
69.7 IPS
 
Face Detection (F32)
100% 2071
23.8 IPS
 
Face Detection (F16)
97% 7077
81.3 IPS
 
Face Detection (I8)
76% 48736
559.9 IPS
 
Text Classification (F32)
100% 15
5.99 IPS
 
Text Classification (F16)
100% 832
329.2 IPS
 
Machine Translation (F32)
100% 1005
154.9 IPS
 
Machine Translation (F16)
100% 1004
154.8 IPS
 

Compare

Set Baseline Geekbench 6 now available