Geekbench ML Score

351
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 10:24 PM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-A525F
Model IDsamsung SM-A525F
Motherboard atoll
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 15 part 2052 revision 15
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.32 GHz
Memory Information
Size 5.37 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 319
34.1 IPS
 
Image Classification (F16)
100% 452
48.5 IPS
 
Image Classification (I8)
80% 987
105.8 IPS
 
Image Segmentation (F32)
100% 472
2.91 IPS
 
Image Segmentation (F16)
100% 546
3.37 IPS
 
Image Segmentation (I8)
89% 2306
14.2 IPS
 
Pose Estimation (F32)
100% 141
0.57 IPS
 
Pose Estimation (F16)
100% 330
1.34 IPS
 
Pose Estimation (I8)
80% 1130
4.57 IPS
 
Object Detection (F32)
100% 286
10.0 IPS
 
Object Detection (F16)
100% 352
12.3 IPS
 
Object Detection (I8)
52% 488
17.1 IPS
 
Face Detection (F32)
100% 381
4.38 IPS
 
Face Detection (F16)
97% 458
5.27 IPS
 
Face Detection (I8)
75% 1619
18.6 IPS
 
Text Classification (F32)
54% 30
11.7 IPS
 
Text Classification (F16)
54% 32
12.6 IPS
 
Machine Translation (F32)
100% 201
31.0 IPS
 
Machine Translation (F16)
100% 197
30.4 IPS
 

Compare

Set Baseline