Geekbench ML Score

592
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 06:54 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPad mini (5th generation)
Model IDiPad11,2
Motherboard J211AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 2.85 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 467
50.0 IPS
 
Image Classification (F16)
100% 465
49.8 IPS
 
Image Classification (I8)
81% 285
30.5 IPS
 
Image Segmentation (F32)
100% 772
4.77 IPS
 
Image Segmentation (F16)
100% 761
4.70 IPS
 
Image Segmentation (I8)
89% 979
6.05 IPS
 
Pose Estimation (F32)
100% 262
1.06 IPS
 
Pose Estimation (F16)
100% 261
1.06 IPS
 
Pose Estimation (I8)
80% 276
1.12 IPS
 
Object Detection (F32)
100% 714
25.1 IPS
 
Object Detection (F16)
100% 718
25.2 IPS
 
Object Detection (I8)
52% 542
19.0 IPS
 
Face Detection (F32)
100% 901
10.4 IPS
 
Face Detection (F16)
100% 896
10.3 IPS
 
Face Detection (I8)
75% 527
6.06 IPS
 
Text Classification (F32)
100% 772
305.3 IPS
 
Text Classification (F16)
100% 790
312.5 IPS
 
Machine Translation (F32)
100% 993
153.1 IPS
 
Machine Translation (F16)
100% 989
152.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download