Geekbench ML Score

491
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 03 2021 10:28 AM
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% 551
59.0 IPS
 
Image Classification (F16)
100% 301
32.3 IPS
 
Image Classification (I8)
81% 279
29.8 IPS
 
Image Segmentation (F32)
100% 597
3.69 IPS
 
Image Segmentation (F16)
100% 616
3.81 IPS
 
Image Segmentation (I8)
89% 798
4.93 IPS
 
Pose Estimation (F32)
100% 183
0.74 IPS
 
Pose Estimation (F16)
100% 189
0.77 IPS
 
Pose Estimation (I8)
80% 265
1.07 IPS
 
Object Detection (F32)
100% 656
23.0 IPS
 
Object Detection (F16)
100% 283
9.94 IPS
 
Object Detection (I8)
52% 321
11.3 IPS
 
Face Detection (F32)
100% 723
8.31 IPS
 
Face Detection (F16)
100% 680
7.81 IPS
 
Face Detection (I8)
75% 545
6.26 IPS
 
Text Classification (F32)
100% 453
179.1 IPS
 
Text Classification (F16)
100% 1533
606.5 IPS
 
Machine Translation (F32)
100% 1157
178.3 IPS
 
Machine Translation (F16)
100% 871
134.2 IPS
 

Compare

Set Baseline Geekbench 6 now available