Geekbench ML Score

391
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User Mansur892
Upload Date December 08 2022 08:22 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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 298
31.9 IPS
 
Image Classification (F16)
100% 318
34.1 IPS
 
Image Classification (I8)
81% 201
21.6 IPS
 
Image Segmentation (F32)
100% 592
3.66 IPS
 
Image Segmentation (F16)
100% 591
3.65 IPS
 
Image Segmentation (I8)
89% 899
5.55 IPS
 
Pose Estimation (F32)
100% 261
1.06 IPS
 
Pose Estimation (F16)
100% 260
1.05 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 383
13.5 IPS
 
Object Detection (F16)
100% 380
13.3 IPS
 
Object Detection (I8)
52% 307
10.8 IPS
 
Face Detection (F32)
100% 543
6.24 IPS
 
Face Detection (F16)
100% 540
6.21 IPS
 
Face Detection (I8)
75% 523
6.01 IPS
 
Text Classification (F32)
100% 343
135.6 IPS
 
Text Classification (F16)
100% 345
136.3 IPS
 
Machine Translation (F32)
100% 474
73.1 IPS
 
Machine Translation (F16)
100% 476
73.3 IPS
 

Compare

Set Baseline