Geekbench ML Score

1020
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 29 2021 01:17 AM
Views 1

System Information

System Information
Operating System iOS 15.0
Model iPad13,4
Model IDiPad13,4
Motherboard J517AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 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% 942
101.0 IPS
 
Image Classification (F16)
100% 951
101.9 IPS
 
Image Classification (I8)
81% 390
41.8 IPS
 
Image Segmentation (F32)
100% 1253
7.74 IPS
 
Image Segmentation (F16)
100% 1249
7.72 IPS
 
Image Segmentation (I8)
89% 1518
9.37 IPS
 
Pose Estimation (F32)
100% 665
2.69 IPS
 
Pose Estimation (F16)
100% 666
2.70 IPS
 
Pose Estimation (I8)
80% 792
3.21 IPS
 
Object Detection (F32)
100% 1454
51.0 IPS
 
Object Detection (F16)
100% 1457
51.1 IPS
 
Object Detection (I8)
52% 625
21.9 IPS
 
Face Detection (F32)
100% 1645
18.9 IPS
 
Face Detection (F16)
100% 1636
18.8 IPS
 
Face Detection (I8)
75% 811
9.32 IPS
 
Text Classification (F32)
100% 713
282.1 IPS
 
Text Classification (F16)
100% 714
282.3 IPS
 
Machine Translation (F32)
100% 1851
285.2 IPS
 
Machine Translation (F16)
100% 1858
286.4 IPS
 

Compare

Set Baseline Geekbench 6 now available