Geekbench ML Score

829
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 31 2023 01:03 PM
Views 1

System Information

System Information
Operating System Android 12
Model asus ASUS_I002D
Model IDasus ASUS_I002D
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 @ 3.09 GHz
Memory Information
Size 7.49 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 748
80.1 IPS
 
Image Classification (F16)
100% 1172
125.6 IPS
 
Image Classification (I8)
80% 1662
178.1 IPS
 
Image Segmentation (F32)
100% 1134
7.01 IPS
 
Image Segmentation (F16)
100% 1386
8.56 IPS
 
Image Segmentation (I8)
89% 3880
24.0 IPS
 
Pose Estimation (F32)
100% 460
1.86 IPS
 
Pose Estimation (F16)
100% 1720
6.96 IPS
 
Pose Estimation (I8)
80% 5852
23.7 IPS
 
Object Detection (F32)
100% 667
23.4 IPS
 
Object Detection (F16)
100% 823
28.9 IPS
 
Object Detection (I8)
52% 1410
49.5 IPS
 
Face Detection (F32)
100% 1169
13.4 IPS
 
Face Detection (F16)
97% 1496
17.2 IPS
 
Face Detection (I8)
75% 4441
51.0 IPS
 
Text Classification (F32)
54% 18
7.29 IPS
 
Text Classification (F16)
54% 19
7.41 IPS
 
Machine Translation (F32)
100% 581
89.6 IPS
 
Machine Translation (F16)
100% 582
89.7 IPS
 

Compare

Set Baseline Geekbench 6 now available