Geekbench ML Score

543
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 02:09 AM
Views 12

System Information

System Information
Operating System Android 12
Model samsung SM-F936N
Model IDsamsung SM-F936N
Motherboard taro
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 2.02 GHz
Cluster 14 Cores @ 2.02 GHz
Cluster 23 Cores @ 2.75 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 10.99 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 592
63.5 IPS
 
Image Classification (F16)
100% 590
63.3 IPS
 
Image Classification (I8)
81% 188
20.2 IPS
 
Image Segmentation (F32)
100% 796
4.92 IPS
 
Image Segmentation (F16)
100% 789
4.87 IPS
 
Image Segmentation (I8)
89% 1026
6.34 IPS
 
Pose Estimation (F32)
100% 371
1.50 IPS
 
Pose Estimation (F16)
100% 354
1.43 IPS
 
Pose Estimation (I8)
80% 284
1.15 IPS
 
Object Detection (F32)
100% 555
19.5 IPS
 
Object Detection (F16)
100% 539
18.9 IPS
 
Object Detection (I8)
52% 300
10.5 IPS
 
Face Detection (F32)
100% 870
9.99 IPS
 
Face Detection (F16)
100% 880
10.1 IPS
 
Face Detection (I8)
75% 564
6.48 IPS
 
Text Classification (F32)
100% 350
138.5 IPS
 
Text Classification (F16)
100% 350
138.3 IPS
 
Machine Translation (F32)
100% 1119
172.5 IPS
 
Machine Translation (F16)
100% 1117
172.2 IPS
 

Compare

Set Baseline