Geekbench ML Score

1008
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 09:16 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPad13,4
Model IDiPad13,4
Motherboard J517AP
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 7.33 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 951
101.9 IPS
 
Image Classification (F16)
100% 935
100.2 IPS
 
Image Classification (I8)
81% 390
41.8 IPS
 
Image Segmentation (F32)
100% 1259
7.78 IPS
 
Image Segmentation (F16)
100% 1251
7.73 IPS
 
Image Segmentation (I8)
89% 1497
9.25 IPS
 
Pose Estimation (F32)
100% 668
2.70 IPS
 
Pose Estimation (F16)
100% 664
2.69 IPS
 
Pose Estimation (I8)
80% 795
3.22 IPS
 
Object Detection (F32)
100% 1446
50.8 IPS
 
Object Detection (F16)
100% 1442
50.6 IPS
 
Object Detection (I8)
52% 606
21.3 IPS
 
Face Detection (F32)
100% 1635
18.8 IPS
 
Face Detection (F16)
100% 1640
18.8 IPS
 
Face Detection (I8)
75% 819
9.41 IPS
 
Text Classification (F32)
100% 636
251.6 IPS
 
Text Classification (F16)
100% 680
269.0 IPS
 
Machine Translation (F32)
100% 1836
283.0 IPS
 
Machine Translation (F16)
100% 1851
285.3 IPS
 

Compare

Set Baseline Geekbench 6 now available