Geekbench ML Score

1001
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 09:39 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPad13,17
Model IDiPad13,17
Motherboard J408AP
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 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 942
101.0 IPS
 
Image Classification (F16)
100% 937
100.4 IPS
 
Image Classification (I8)
81% 399
42.8 IPS
 
Image Segmentation (F32)
100% 1329
8.21 IPS
 
Image Segmentation (F16)
100% 1329
8.21 IPS
 
Image Segmentation (I8)
89% 1485
9.17 IPS
 
Pose Estimation (F32)
100% 667
2.70 IPS
 
Pose Estimation (F16)
100% 667
2.70 IPS
 
Pose Estimation (I8)
80% 799
3.23 IPS
 
Object Detection (F32)
100% 1433
50.3 IPS
 
Object Detection (F16)
100% 1424
50.0 IPS
 
Object Detection (I8)
52% 611
21.4 IPS
 
Face Detection (F32)
100% 1623
18.6 IPS
 
Face Detection (F16)
100% 1628
18.7 IPS
 
Face Detection (I8)
75% 795
9.13 IPS
 
Text Classification (F32)
100% 608
240.6 IPS
 
Text Classification (F16)
100% 613
242.5 IPS
 
Machine Translation (F32)
100% 1796
276.9 IPS
 
Machine Translation (F16)
100% 1793
276.4 IPS
 

Compare

Set Baseline