Geekbench ML Score

700
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 28 2021 08:13 PM
Views 1

System Information

System Information
Operating System iOS 15.0
Model iPhone 11 Pro
Model IDiPhone12,3
Motherboard D421AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.68 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 531
56.9 IPS
 
Image Classification (F16)
100% 528
56.5 IPS
 
Image Classification (I8)
81% 303
32.4 IPS
 
Image Segmentation (F32)
100% 855
5.28 IPS
 
Image Segmentation (F16)
100% 847
5.23 IPS
 
Image Segmentation (I8)
89% 1110
6.86 IPS
 
Pose Estimation (F32)
100% 267
1.08 IPS
 
Pose Estimation (F16)
100% 155
0.63 IPS
 
Pose Estimation (I8)
80% 322
1.30 IPS
 
Object Detection (F32)
100% 782
27.4 IPS
 
Object Detection (F16)
100% 784
27.5 IPS
 
Object Detection (I8)
52% 606
21.3 IPS
 
Face Detection (F32)
100% 947
10.9 IPS
 
Face Detection (F16)
100% 958
11.0 IPS
 
Face Detection (I8)
75% 714
8.20 IPS
 
Text Classification (F32)
100% 2004
792.7 IPS
 
Text Classification (F16)
100% 1830
723.6 IPS
 
Machine Translation (F32)
100% 1202
185.2 IPS
 
Machine Translation (F16)
100% 1213
187.0 IPS
 

Compare

Set Baseline Geekbench 6 now available