Geekbench ML Score

2702
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 17 2022 01:06 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad13,16
Model IDiPad13,16
Motherboard J407AP
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 7.45 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6076
651.0 IPS
 
Image Classification (F16)
100% 6099
653.5 IPS
 
Image Classification (I8)
81% 688
73.7 IPS
 
Image Segmentation (F32)
100% 2224
13.7 IPS
 
Image Segmentation (F16)
100% 2220
13.7 IPS
 
Image Segmentation (I8)
89% 1235
7.63 IPS
 
Pose Estimation (F32)
100% 19743
79.9 IPS
 
Pose Estimation (F16)
100% 19571
79.2 IPS
 
Pose Estimation (I8)
80% 236
0.95 IPS
 
Object Detection (F32)
100% 7292
255.9 IPS
 
Object Detection (F16)
100% 7340
257.6 IPS
 
Object Detection (I8)
52% 971
34.1 IPS
 
Face Detection (F32)
100% 7915
90.9 IPS
 
Face Detection (F16)
100% 7928
91.1 IPS
 
Face Detection (I8)
75% 950
10.9 IPS
 
Text Classification (F32)
100% 1048
414.5 IPS
 
Text Classification (F16)
100% 1046
413.7 IPS
 
Machine Translation (F32)
100% 1828
281.7 IPS
 
Machine Translation (F16)
100% 1815
279.8 IPS
 

Compare

Set Baseline Geekbench 6 now available