Geekbench ML Score

1014
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 15 2022 01:21 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad13,17
Model IDiPad13,17
Motherboard J408AP
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 7.45 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 939
100.6 IPS
 
Image Classification (F16)
100% 941
100.8 IPS
 
Image Classification (I8)
81% 382
41.0 IPS
 
Image Segmentation (F32)
100% 1333
8.24 IPS
 
Image Segmentation (F16)
100% 1332
8.23 IPS
 
Image Segmentation (I8)
89% 1537
9.49 IPS
 
Pose Estimation (F32)
100% 670
2.71 IPS
 
Pose Estimation (F16)
100% 671
2.72 IPS
 
Pose Estimation (I8)
80% 802
3.25 IPS
 
Object Detection (F32)
100% 1462
51.3 IPS
 
Object Detection (F16)
100% 1463
51.3 IPS
 
Object Detection (I8)
52% 620
21.8 IPS
 
Face Detection (F32)
100% 1647
18.9 IPS
 
Face Detection (F16)
100% 1639
18.8 IPS
 
Face Detection (I8)
75% 808
9.28 IPS
 
Text Classification (F32)
100% 651
257.6 IPS
 
Text Classification (F16)
100% 617
244.1 IPS
 
Machine Translation (F32)
100% 1850
285.2 IPS
 
Machine Translation (F16)
100% 1849
284.9 IPS
 

Compare

Set Baseline Geekbench 6 now available