Geekbench ML Score

256
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 09:50 PM
Views 1

System Information

System Information
Operating System Android 12
Model samsung SM-A536W
Model IDsamsung SM-A536W
Motherboard s5e8825
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 5.26 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 151
16.2 IPS
 
Image Classification (F16)
100% 146
15.7 IPS
 
Image Classification (I8)
81% 172
18.4 IPS
 
Image Segmentation (F32)
100% 372
2.30 IPS
 
Image Segmentation (F16)
100% 379
2.34 IPS
 
Image Segmentation (I8)
89% 541
3.34 IPS
 
Pose Estimation (F32)
100% 137
0.55 IPS
 
Pose Estimation (F16)
100% 140
0.57 IPS
 
Pose Estimation (I8)
80% 132
0.54 IPS
 
Object Detection (F32)
100% 221
7.76 IPS
 
Object Detection (F16)
100% 225
7.91 IPS
 
Object Detection (I8)
52% 247
8.67 IPS
 
Face Detection (F32)
100% 351
4.03 IPS
 
Face Detection (F16)
100% 348
3.99 IPS
 
Face Detection (I8)
75% 361
4.15 IPS
 
Text Classification (F32)
100% 333
131.9 IPS
 
Text Classification (F16)
100% 333
131.7 IPS
 
Machine Translation (F32)
100% 364
56.2 IPS
 
Machine Translation (F16)
100% 360
55.5 IPS
 

Compare

Set Baseline