Geekbench ML Score

872
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 06 2021 04:53 AM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 358
38.4 IPS
 
Image Classification (F16)
100% 519
55.6 IPS
 
Image Classification (I8)
81% 669
71.6 IPS
 
Image Segmentation (F32)
100% 737
4.55 IPS
 
Image Segmentation (F16)
100% 742
4.58 IPS
 
Image Segmentation (I8)
89% 1416
8.74 IPS
 
Pose Estimation (F32)
100% 384
1.55 IPS
 
Pose Estimation (F16)
100% 398
1.61 IPS
 
Pose Estimation (I8)
80% 461
1.87 IPS
 
Object Detection (F32)
100% 966
33.9 IPS
 
Object Detection (F16)
100% 982
34.5 IPS
 
Object Detection (I8)
52% 1047
36.7 IPS
 
Face Detection (F32)
100% 1006
11.6 IPS
 
Face Detection (F16)
100% 1148
13.2 IPS
 
Face Detection (I8)
75% 919
10.6 IPS
 
Text Classification (F32)
100% 1919
759.2 IPS
 
Text Classification (F16)
100% 1956
773.8 IPS
 
Machine Translation (F32)
100% 1673
257.8 IPS
 
Machine Translation (F16)
100% 1670
257.3 IPS
 

Compare

Set Baseline Geekbench 6 now available