Geekbench ML Score

832
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User jmurphyau
Upload Date January 14 2022 11:50 PM
Views 2

System Information

System Information
Operating System iOS 15.3
Model iPhone 12 Pro
Model IDiPhone13,3
Motherboard D53pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 592
63.4 IPS
 
Image Classification (F16)
100% 577
61.8 IPS
 
Image Classification (I8)
81% 396
42.4 IPS
 
Image Segmentation (F32)
100% 939
5.80 IPS
 
Image Segmentation (F16)
100% 892
5.51 IPS
 
Image Segmentation (I8)
89% 1344
8.30 IPS
 
Pose Estimation (F32)
100% 332
1.34 IPS
 
Pose Estimation (F16)
100% 325
1.31 IPS
 
Pose Estimation (I8)
80% 412
1.67 IPS
 
Object Detection (F32)
100% 819
28.7 IPS
 
Object Detection (F16)
100% 833
29.2 IPS
 
Object Detection (I8)
52% 674
23.7 IPS
 
Face Detection (F32)
100% 1031
11.8 IPS
 
Face Detection (F16)
100% 996
11.4 IPS
 
Face Detection (I8)
75% 803
9.22 IPS
 
Text Classification (F32)
100% 1982
783.8 IPS
 
Text Classification (F16)
100% 2115
836.6 IPS
 
Machine Translation (F32)
100% 1686
259.8 IPS
 
Machine Translation (F16)
100% 1686
259.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download