Geekbench ML Score

1016
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 06:19 AM
Views 1

System Information

System Information
Operating System iOS 15.0.1
Model iPad13,8
Model IDiPad13,8
Motherboard J522AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.20 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 932
99.8 IPS
 
Image Classification (F16)
100% 933
100.0 IPS
 
Image Classification (I8)
81% 403
43.2 IPS
 
Image Segmentation (F32)
100% 1243
7.68 IPS
 
Image Segmentation (F16)
100% 1242
7.67 IPS
 
Image Segmentation (I8)
89% 1477
9.12 IPS
 
Pose Estimation (F32)
100% 666
2.70 IPS
 
Pose Estimation (F16)
100% 672
2.72 IPS
 
Pose Estimation (I8)
80% 799
3.23 IPS
 
Object Detection (F32)
100% 1463
51.3 IPS
 
Object Detection (F16)
100% 1477
51.8 IPS
 
Object Detection (I8)
52% 609
21.4 IPS
 
Face Detection (F32)
100% 1636
18.8 IPS
 
Face Detection (F16)
100% 1651
19.0 IPS
 
Face Detection (I8)
75% 796
9.15 IPS
 
Text Classification (F32)
100% 742
293.5 IPS
 
Text Classification (F16)
100% 664
262.7 IPS
 
Machine Translation (F32)
100% 1851
285.2 IPS
 
Machine Translation (F16)
100% 1854
285.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download