Geekbench ML Score

2706
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 05 2022 02:50 PM
Views 3

System Information

System Information
Operating System Android 12
Model Sony XQ-CT54
Model IDSony XQ-CT54
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 10.81 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1285
137.7 IPS
 
Image Classification (F16)
100% 9170
982.5 IPS
 
Image Classification (I8)
80% 22111
2.37 KIPS
 
Image Segmentation (F32)
100% 2735
16.9 IPS
 
Image Segmentation (F16)
100% 7134
44.1 IPS
 
Image Segmentation (I8)
89% 40209
248.4 IPS
 
Pose Estimation (F32)
100% 607
2.46 IPS
 
Pose Estimation (F16)
100% 10194
41.3 IPS
 
Pose Estimation (I8)
80% 55401
224.2 IPS
 
Object Detection (F32)
100% 1008
35.4 IPS
 
Object Detection (F16)
100% 1769
62.1 IPS
 
Object Detection (I8)
53% 1988
69.8 IPS
 
Face Detection (F32)
100% 1929
22.2 IPS
 
Face Detection (F16)
97% 5513
63.3 IPS
 
Face Detection (I8)
76% 42373
486.8 IPS
 
Text Classification (F32)
100% 9
3.69 IPS
 
Text Classification (F16)
100% 501
198.0 IPS
 
Machine Translation (F32)
100% 635
97.8 IPS
 
Machine Translation (F16)
100% 514
79.3 IPS
 

Compare

Set Baseline Geekbench 6 now available