Geekbench ML Score

2703
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 06 2022 08:46 PM
Views 3

System Information

System Information
Operating System iOS 15.7
Model iPad13,16
Model IDiPad13,16
Motherboard J407AP
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 Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6103
653.9 IPS
 
Image Classification (F16)
100% 6088
652.3 IPS
 
Image Classification (I8)
81% 677
72.5 IPS
 
Image Segmentation (F32)
100% 2219
13.7 IPS
 
Image Segmentation (F16)
100% 2217
13.7 IPS
 
Image Segmentation (I8)
89% 1233
7.61 IPS
 
Pose Estimation (F32)
100% 19037
77.0 IPS
 
Pose Estimation (F16)
100% 19079
77.2 IPS
 
Pose Estimation (I8)
80% 236
0.96 IPS
 
Object Detection (F32)
100% 7377
258.9 IPS
 
Object Detection (F16)
100% 7758
272.2 IPS
 
Object Detection (I8)
52% 968
34.0 IPS
 
Face Detection (F32)
100% 7909
90.9 IPS
 
Face Detection (F16)
100% 7893
90.7 IPS
 
Face Detection (I8)
75% 949
10.9 IPS
 
Text Classification (F32)
100% 1059
418.8 IPS
 
Text Classification (F16)
100% 1058
418.6 IPS
 
Machine Translation (F32)
100% 1822
280.9 IPS
 
Machine Translation (F16)
100% 1832
282.4 IPS
 

Compare

Set Baseline Geekbench 6 now available