Geekbench ML Score

796
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 05:59 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi M2012K11AG
Model IDXiaomi M2012K11AG
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 @ 3.19 GHz
Memory Information
Size 5.48 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 775
83.1 IPS
 
Image Classification (F16)
100% 1199
128.5 IPS
 
Image Classification (I8)
80% 2787
298.6 IPS
 
Image Segmentation (F32)
100% 1010
6.24 IPS
 
Image Segmentation (F16)
100% 1149
7.09 IPS
 
Image Segmentation (I8)
89% 5837
36.1 IPS
 
Pose Estimation (F32)
100% 471
1.91 IPS
 
Pose Estimation (F16)
100% 1767
7.15 IPS
 
Pose Estimation (I8)
80% 3603
14.6 IPS
 
Object Detection (F32)
100% 496
17.4 IPS
 
Object Detection (F16)
100% 803
28.2 IPS
 
Object Detection (I8)
52% 1250
43.9 IPS
 
Face Detection (F32)
100% 1078
12.4 IPS
 
Face Detection (F16)
97% 1292
14.8 IPS
 
Face Detection (I8)
75% 4677
53.7 IPS
 
Text Classification (F32)
54% 15
6.05 IPS
 
Text Classification (F16)
54% 15
5.98 IPS
 
Machine Translation (F32)
100% 590
91.0 IPS
 
Machine Translation (F16)
100% 584
90.0 IPS
 

Compare

Set Baseline