Geekbench ML Score

461
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 02:21 AM
Views 9

System Information

System Information
Operating System Android 12
Model samsung SM-X706N
Model IDsamsung SM-X706N
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 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 431
46.2 IPS
 
Image Classification (F16)
100% 424
45.4 IPS
 
Image Classification (I8)
81% 174
18.6 IPS
 
Image Segmentation (F32)
100% 719
4.44 IPS
 
Image Segmentation (F16)
100% 712
4.40 IPS
 
Image Segmentation (I8)
89% 811
5.01 IPS
 
Pose Estimation (F32)
100% 285
1.15 IPS
 
Pose Estimation (F16)
100% 275
1.11 IPS
 
Pose Estimation (I8)
80% 227
0.92 IPS
 
Object Detection (F32)
100% 434
15.2 IPS
 
Object Detection (F16)
100% 430
15.1 IPS
 
Object Detection (I8)
52% 279
9.78 IPS
 
Face Detection (F32)
100% 696
8.00 IPS
 
Face Detection (F16)
100% 718
8.25 IPS
 
Face Detection (I8)
75% 487
5.60 IPS
 
Text Classification (F32)
100% 346
137.0 IPS
 
Text Classification (F16)
100% 351
138.7 IPS
 
Machine Translation (F32)
100% 1066
164.3 IPS
 
Machine Translation (F16)
100% 1065
164.1 IPS
 

Compare

Set Baseline