Geekbench ML Score

692
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:56 AM
Views 3

System Information

System Information
Operating System Android 11
Model samsung SM-T875N
Model IDsamsung SM-T875N
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 3.09 GHz
Memory Information
Size 5.45 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 705
75.6 IPS
 
Image Classification (F16)
100% 1135
121.6 IPS
 
Image Classification (I8)
80% 1292
138.4 IPS
 
Image Segmentation (F32)
100% 886
5.47 IPS
 
Image Segmentation (F16)
100% 1125
6.95 IPS
 
Image Segmentation (I8)
89% 2820
17.4 IPS
 
Pose Estimation (F32)
100% 463
1.87 IPS
 
Pose Estimation (F16)
100% 1685
6.82 IPS
 
Pose Estimation (I8)
80% 5275
21.3 IPS
 
Object Detection (F32)
100% 544
19.1 IPS
 
Object Detection (F16)
100% 613
21.5 IPS
 
Object Detection (I8)
52% 1226
43.0 IPS
 
Face Detection (F32)
100% 972
11.2 IPS
 
Face Detection (F16)
97% 1126
12.9 IPS
 
Face Detection (I8)
75% 4229
48.6 IPS
 
Text Classification (F32)
54% 11
4.33 IPS
 
Text Classification (F16)
54% 11
4.22 IPS
 
Machine Translation (F32)
100% 593
91.3 IPS
 
Machine Translation (F16)
100% 573
88.4 IPS
 

Compare

Set Baseline Geekbench 6 now available