Geekbench ML Score

379
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 03:20 PM
Views 1

System Information

System Information
Operating System Android 10
Model samsung SM-G965F
Model IDsamsung SM-G965F
Motherboard exynos9810
Governorschedutil
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 2 revision 0
Base Frequency 1.79 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 24 Cores @ 2.70 GHz
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 463
49.6 IPS
 
Image Classification (F16)
100% 460
49.2 IPS
 
Image Classification (I8)
80% 565
60.5 IPS
 
Image Segmentation (F32)
100% 312
1.93 IPS
 
Image Segmentation (F16)
100% 324
2.00 IPS
 
Image Segmentation (I8)
89% 1040
6.43 IPS
 
Pose Estimation (F32)
100% 427
1.73 IPS
 
Pose Estimation (F16)
100% 426
1.73 IPS
 
Pose Estimation (I8)
80% 283
1.15 IPS
 
Object Detection (F32)
100% 223
7.84 IPS
 
Object Detection (F16)
100% 220
7.74 IPS
 
Object Detection (I8)
53% 266
9.35 IPS
 
Face Detection (F32)
100% 559
6.43 IPS
 
Face Detection (F16)
100% 560
6.43 IPS
 
Face Detection (I8)
75% 929
10.7 IPS
 
Text Classification (F32)
100% 154
61.0 IPS
 
Text Classification (F16)
100% 158
62.5 IPS
 
Machine Translation (F32)
100% 416
64.0 IPS
 
Machine Translation (F16)
100% 399
61.5 IPS
 

Compare

Set Baseline