Geekbench ML Score

2661
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date May 26 2021 08:17 PM
Views 1

System Information

System Information
Operating System iOS 14.6
Model iPad13,11
Model IDiPad13,11
Motherboard J523xAP
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 15.22 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 5695
610.2 IPS
 
Image Classification (F16)
100% 6013
644.2 IPS
 
Image Classification (I8)
81% 694
74.3 IPS
 
Image Segmentation (F32)
100% 1975
12.2 IPS
 
Image Segmentation (F16)
100% 1974
12.2 IPS
 
Image Segmentation (I8)
89% 1270
7.85 IPS
 
Pose Estimation (F32)
100% 19828
80.2 IPS
 
Pose Estimation (F16)
100% 19228
77.8 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 7240
254.1 IPS
 
Object Detection (F16)
100% 7076
248.3 IPS
 
Object Detection (I8)
52% 986
34.6 IPS
 
Face Detection (F32)
100% 7465
85.8 IPS
 
Face Detection (F16)
100% 7500
86.2 IPS
 
Face Detection (I8)
75% 961
11.0 IPS
 
Text Classification (F32)
100% 1101
435.4 IPS
 
Text Classification (F16)
100% 1060
419.3 IPS
 
Machine Translation (F32)
100% 1861
286.8 IPS
 
Machine Translation (F16)
100% 1866
287.6 IPS
 

Compare

Set Baseline Geekbench 6 now available