Geekbench ML Score

313
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 08:58 AM
Views 1

System Information

System Information
Operating System Android 11
Model samsung SM-A525F
Model IDsamsung SM-A525F
Motherboard atoll
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 15 part 2052 revision 15
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.32 GHz
Memory Information
Size 5.37 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 321
34.4 IPS
 
Image Classification (F16)
100% 454
48.6 IPS
 
Image Classification (I8)
80% 912
97.7 IPS
 
Image Segmentation (F32)
100% 402
2.48 IPS
 
Image Segmentation (F16)
100% 540
3.34 IPS
 
Image Segmentation (I8)
89% 2277
14.1 IPS
 
Pose Estimation (F32)
100% 140
0.57 IPS
 
Pose Estimation (F16)
100% 330
1.33 IPS
 
Pose Estimation (I8)
80% 1110
4.49 IPS
 
Object Detection (F32)
100% 284
9.98 IPS
 
Object Detection (F16)
100% 247
8.68 IPS
 
Object Detection (I8)
52% 461
16.2 IPS
 
Face Detection (F32)
100% 353
4.05 IPS
 
Face Detection (F16)
97% 417
4.80 IPS
 
Face Detection (I8)
75% 1483
17.0 IPS
 
Text Classification (F32)
54% 15
6.03 IPS
 
Text Classification (F16)
54% 14
5.55 IPS
 
Machine Translation (F32)
100% 230
35.4 IPS
 
Machine Translation (F16)
100% 229
35.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download