Geekbench ML Score

401
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:50 AM
Views 5

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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 446
47.8 IPS
 
Image Classification (F16)
100% 262
28.0 IPS
 
Image Classification (I8)
81% 188
20.1 IPS
 
Image Segmentation (F32)
100% 612
3.78 IPS
 
Image Segmentation (F16)
100% 575
3.55 IPS
 
Image Segmentation (I8)
89% 870
5.38 IPS
 
Pose Estimation (F32)
100% 264
1.07 IPS
 
Pose Estimation (F16)
100% 255
1.03 IPS
 
Pose Estimation (I8)
80% 233
0.94 IPS
 
Object Detection (F32)
100% 336
11.8 IPS
 
Object Detection (F16)
100% 352
12.3 IPS
 
Object Detection (I8)
52% 315
11.1 IPS
 
Face Detection (F32)
100% 633
7.27 IPS
 
Face Detection (F16)
100% 551
6.33 IPS
 
Face Detection (I8)
75% 544
6.25 IPS
 
Text Classification (F32)
100% 345
136.4 IPS
 
Text Classification (F16)
100% 344
136.2 IPS
 
Machine Translation (F32)
100% 587
90.5 IPS
 
Machine Translation (F16)
100% 571
88.0 IPS
 

Compare

Set Baseline