Geekbench ML Score

2527
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 08:59 PM
Views 19

System Information

System Information
Operating System iOS 15.0
Model iPad14,2
Model IDiPad14,2
Motherboard J311AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.94 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.78 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4981
533.7 IPS
 
Image Classification (F16)
100% 5029
538.8 IPS
 
Image Classification (I8)
81% 633
67.8 IPS
 
Image Segmentation (F32)
100% 1904
11.8 IPS
 
Image Segmentation (F16)
100% 1902
11.7 IPS
 
Image Segmentation (I8)
89% 1150
7.11 IPS
 
Pose Estimation (F32)
100% 19300
78.1 IPS
 
Pose Estimation (F16)
100% 20307
82.2 IPS
 
Pose Estimation (I8)
80% 220
0.89 IPS
 
Object Detection (F32)
100% 6437
225.9 IPS
 
Object Detection (F16)
100% 6578
230.8 IPS
 
Object Detection (I8)
52% 900
31.6 IPS
 
Face Detection (F32)
100% 7679
88.2 IPS
 
Face Detection (F16)
100% 7617
87.5 IPS
 
Face Detection (I8)
75% 865
9.94 IPS
 
Text Classification (F32)
100% 1083
428.5 IPS
 
Text Classification (F16)
100% 1094
432.5 IPS
 
Machine Translation (F32)
100% 1853
285.6 IPS
 
Machine Translation (F16)
100% 1855
285.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download