Geekbench ML Score

306
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 02:17 PM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-A528B
Model IDsamsung SM-A528B
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 5.24 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 234
25.1 IPS
 
Image Classification (F16)
100% 232
24.8 IPS
 
Image Classification (I8)
81% 161
17.2 IPS
 
Image Segmentation (F32)
100% 382
2.36 IPS
 
Image Segmentation (F16)
100% 402
2.49 IPS
 
Image Segmentation (I8)
89% 310
1.91 IPS
 
Pose Estimation (F32)
100% 246
0.99 IPS
 
Pose Estimation (F16)
100% 235
0.95 IPS
 
Pose Estimation (I8)
80% 66
0.27 IPS
 
Object Detection (F32)
100% 329
11.5 IPS
 
Object Detection (F16)
100% 319
11.2 IPS
 
Object Detection (I8)
52% 268
9.42 IPS
 
Face Detection (F32)
100% 439
5.05 IPS
 
Face Detection (F16)
100% 430
4.94 IPS
 
Face Detection (I8)
75% 326
3.74 IPS
 
Text Classification (F32)
100% 524
207.3 IPS
 
Text Classification (F16)
100% 535
211.6 IPS
 
Machine Translation (F32)
100% 474
73.0 IPS
 
Machine Translation (F16)
100% 478
73.7 IPS
 

Compare

Set Baseline