Geekbench ML Score

971
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 07:13 AM
Views 2

System Information

System Information
Operating System Android 11
Model asus ASUS_I007D
Model IDasus ASUS_I007D
Motherboard lahaina
Governorschedutil
CPU Information
Name ARM Venus
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 14.84 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 994
106.5 IPS
 
Image Classification (F16)
100% 1698
181.9 IPS
 
Image Classification (I8)
79% 5012
537.0 IPS
 
Image Segmentation (F32)
100% 2436
15.0 IPS
 
Image Segmentation (F16)
71% 3556
22.0 IPS
 
Image Segmentation (I8)
69% 3616
22.3 IPS
 
Pose Estimation (F32)
100% 568
2.30 IPS
 
Pose Estimation (F16)
100% 1998
8.09 IPS
 
Pose Estimation (I8)
53% 17318
70.1 IPS
 
Object Detection (F32)
100% 904
31.7 IPS
 
Object Detection (F16)
100% 1240
43.5 IPS
 
Object Detection (I8)
52% 475
16.7 IPS
 
Face Detection (F32)
100% 479
5.51 IPS
 
Face Detection (F16)
100% 632
7.26 IPS
 
Face Detection (I8)
75% 8225
94.5 IPS
 
Text Classification (F32)
100% 12
4.76 IPS
 
Text Classification (F16)
46% 12
4.75 IPS
 
Machine Translation (F32)
100% 761
117.2 IPS
 
Machine Translation (F16)
100% 762
117.4 IPS
 

Compare

Set Baseline Geekbench 6 now available