Geekbench ML Score

335
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Mansur892
Upload Date December 08 2022 08:29 AM
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 7.19 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 305
32.7 IPS
 
Image Classification (F16)
100% 316
33.8 IPS
 
Image Classification (I8)
81% 219
23.4 IPS
 
Image Segmentation (F32)
100% 507
3.13 IPS
 
Image Segmentation (F16)
100% 503
3.11 IPS
 
Image Segmentation (I8)
89% 414
2.56 IPS
 
Pose Estimation (F32)
100% 249
1.01 IPS
 
Pose Estimation (F16)
100% 248
1.00 IPS
 
Pose Estimation (I8)
80% 66
0.27 IPS
 
Object Detection (F32)
100% 326
11.4 IPS
 
Object Detection (F16)
100% 321
11.3 IPS
 
Object Detection (I8)
52% 269
9.43 IPS
 
Face Detection (F32)
100% 439
5.04 IPS
 
Face Detection (F16)
100% 441
5.07 IPS
 
Face Detection (I8)
75% 326
3.75 IPS
 
Text Classification (F32)
100% 532
210.5 IPS
 
Text Classification (F16)
100% 531
210.0 IPS
 
Machine Translation (F32)
100% 460
71.0 IPS
 
Machine Translation (F16)
100% 468
72.1 IPS
 

Compare

Set Baseline