Geekbench ML Score

1011
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 28 2021 08:17 PM
Views 2

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 3.20 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% 971
104.1 IPS
 
Image Classification (F16)
100% 942
100.9 IPS
 
Image Classification (I8)
81% 389
41.6 IPS
 
Image Segmentation (F32)
100% 1251
7.72 IPS
 
Image Segmentation (F16)
100% 1261
7.79 IPS
 
Image Segmentation (I8)
89% 1487
9.18 IPS
 
Pose Estimation (F32)
100% 669
2.71 IPS
 
Pose Estimation (F16)
100% 667
2.70 IPS
 
Pose Estimation (I8)
80% 791
3.20 IPS
 
Object Detection (F32)
100% 1507
52.9 IPS
 
Object Detection (F16)
100% 1427
50.1 IPS
 
Object Detection (I8)
52% 587
20.6 IPS
 
Face Detection (F32)
100% 1686
19.4 IPS
 
Face Detection (F16)
100% 1678
19.3 IPS
 
Face Detection (I8)
75% 816
9.37 IPS
 
Text Classification (F32)
100% 655
259.0 IPS
 
Text Classification (F16)
100% 646
255.7 IPS
 
Machine Translation (F32)
100% 1848
284.8 IPS
 
Machine Translation (F16)
100% 1849
284.9 IPS
 

Compare

Set Baseline Geekbench 6 now available