Geekbench ML Score

374
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 09:55 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 NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 226
24.2 IPS
 
Image Classification (F16)
100% 225
24.2 IPS
 
Image Classification (I8)
81% 217
23.2 IPS
 
Image Segmentation (F32)
100% 435
2.68 IPS
 
Image Segmentation (F16)
100% 435
2.69 IPS
 
Image Segmentation (I8)
89% 685
4.23 IPS
 
Pose Estimation (F32)
100% 196
0.79 IPS
 
Pose Estimation (F16)
100% 627
2.54 IPS
 
Pose Estimation (I8)
80% 609
2.46 IPS
 
Object Detection (F32)
100% 345
12.1 IPS
 
Object Detection (F16)
99% 525
18.4 IPS
 
Object Detection (I8)
52% 266
9.32 IPS
 
Face Detection (F32)
100% 370
4.25 IPS
 
Face Detection (F16)
100% 366
4.21 IPS
 
Face Detection (I8)
75% 321
3.69 IPS
 
Text Classification (F32)
100% 517
204.6 IPS
 
Text Classification (F16)
100% 517
204.5 IPS
 
Machine Translation (F32)
100% 361
55.6 IPS
 
Machine Translation (F16)
100% 361
55.7 IPS
 

Compare

Set Baseline