Geekbench ML Score

2554
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 05 2022 02:45 PM
Views 2

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% 1206
129.2 IPS
 
Image Classification (F16)
100% 8301
889.4 IPS
 
Image Classification (I8)
80% 18274
1.96 KIPS
 
Image Segmentation (F32)
100% 2565
15.8 IPS
 
Image Segmentation (F16)
100% 7068
43.7 IPS
 
Image Segmentation (I8)
89% 25750
159.1 IPS
 
Pose Estimation (F32)
100% 601
2.43 IPS
 
Pose Estimation (F16)
100% 10598
42.9 IPS
 
Pose Estimation (I8)
80% 51479
208.3 IPS
 
Object Detection (F32)
100% 846
29.7 IPS
 
Object Detection (F16)
100% 1487
52.2 IPS
 
Object Detection (I8)
53% 1651
57.9 IPS
 
Face Detection (F32)
100% 1912
22.0 IPS
 
Face Detection (F16)
97% 6625
76.1 IPS
 
Face Detection (I8)
76% 41988
482.4 IPS
 
Text Classification (F32)
100% 9
3.70 IPS
 
Text Classification (F16)
100% 488
193.2 IPS
 
Machine Translation (F32)
100% 635
97.8 IPS
 
Machine Translation (F16)
100% 635
97.9 IPS
 

Compare

Set Baseline Geekbench 6 now available