Geekbench ML Score

422
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 06:43 AM
Views 2

System Information

System Information
Operating System Android 13
Model Samsung Galaxy S20 FE 5G
Model IDsamsung SM-G781B
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 @ 2.84 GHz
Memory Information
Size 7.44 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 447
47.9 IPS
 
Image Classification (F16)
100% 445
47.7 IPS
 
Image Classification (I8)
81% 201
21.5 IPS
 
Image Segmentation (F32)
100% 605
3.74 IPS
 
Image Segmentation (F16)
100% 611
3.77 IPS
 
Image Segmentation (I8)
89% 835
5.16 IPS
 
Pose Estimation (F32)
100% 263
1.07 IPS
 
Pose Estimation (F16)
100% 268
1.09 IPS
 
Pose Estimation (I8)
80% 239
0.97 IPS
 
Object Detection (F32)
100% 418
14.7 IPS
 
Object Detection (F16)
100% 361
12.7 IPS
 
Object Detection (I8)
52% 289
10.1 IPS
 
Face Detection (F32)
100% 570
6.55 IPS
 
Face Detection (F16)
100% 596
6.85 IPS
 
Face Detection (I8)
75% 558
6.41 IPS
 
Text Classification (F32)
100% 396
156.6 IPS
 
Text Classification (F16)
100% 396
156.6 IPS
 
Machine Translation (F32)
100% 544
83.8 IPS
 
Machine Translation (F16)
100% 542
83.6 IPS
 

Compare

Set Baseline