Geekbench ML Score

306
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 22 2023 12:42 PM
Views 1

System Information

System Information
Operating System Android 13
Model Nothing A063
Model IDNothing A063
Motherboard Spacewar
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.40 GHz
Cluster 31 Core @ 2.52 GHz
Memory Information
Size 7.09 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 263
28.2 IPS
 
Image Classification (F16)
100% 266
28.5 IPS
 
Image Classification (I8)
81% 199
21.3 IPS
 
Image Segmentation (F32)
100% 452
2.79 IPS
 
Image Segmentation (F16)
100% 487
3.01 IPS
 
Image Segmentation (I8)
89% 376
2.32 IPS
 
Pose Estimation (F32)
100% 235
0.95 IPS
 
Pose Estimation (F16)
100% 236
0.95 IPS
 
Pose Estimation (I8)
80% 60
0.24 IPS
 
Object Detection (F32)
100% 288
10.1 IPS
 
Object Detection (F16)
100% 288
10.1 IPS
 
Object Detection (I8)
52% 245
8.60 IPS
 
Face Detection (F32)
100% 410
4.71 IPS
 
Face Detection (F16)
100% 406
4.66 IPS
 
Face Detection (I8)
75% 294
3.38 IPS
 
Text Classification (F32)
100% 483
191.1 IPS
 
Text Classification (F16)
100% 485
191.9 IPS
 
Machine Translation (F32)
100% 449
69.1 IPS
 
Machine Translation (F16)
100% 449
69.1 IPS
 

Compare

Set Baseline Geekbench 6 now available