Geekbench ML Score

871
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 07:52 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad mini (6th generation)
Model IDiPad14,1
Motherboard J310AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.92 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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 737
78.9 IPS
 
Image Classification (F16)
100% 685
73.4 IPS
 
Image Classification (I8)
81% 454
48.6 IPS
 
Image Segmentation (F32)
100% 1023
6.32 IPS
 
Image Segmentation (F16)
100% 978
6.04 IPS
 
Image Segmentation (I8)
89% 1391
8.59 IPS
 
Pose Estimation (F32)
100% 382
1.55 IPS
 
Pose Estimation (F16)
100% 376
1.52 IPS
 
Pose Estimation (I8)
80% 455
1.84 IPS
 
Object Detection (F32)
100% 961
33.7 IPS
 
Object Detection (F16)
100% 974
34.2 IPS
 
Object Detection (I8)
52% 735
25.8 IPS
 
Face Detection (F32)
100% 1232
14.2 IPS
 
Face Detection (F16)
100% 1188
13.6 IPS
 
Face Detection (I8)
75% 842
9.67 IPS
 
Text Classification (F32)
100% 1146
453.2 IPS
 
Text Classification (F16)
100% 1056
417.6 IPS
 
Machine Translation (F32)
100% 1851
285.3 IPS
 
Machine Translation (F16)
100% 1861
286.8 IPS
 

Compare

Set Baseline