Geekbench ML Score

293
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 24 2021 01:08 AM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone 6s Plus
Model IDiPhone8,2
Motherboard N66AP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.85 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 203
21.8 IPS
 
Image Classification (F16)
100% 203
21.7 IPS
 
Image Classification (I8)
81% 330
35.3 IPS
 
Image Segmentation (F32)
100% 364
2.25 IPS
 
Image Segmentation (F16)
100% 352
2.17 IPS
 
Image Segmentation (I8)
89% 610
3.77 IPS
 
Pose Estimation (F32)
100% 109
0.44 IPS
 
Pose Estimation (F16)
100% 101
0.41 IPS
 
Pose Estimation (I8)
80% 103
0.42 IPS
 
Object Detection (F32)
100% 321
11.3 IPS
 
Object Detection (F16)
100% 318
11.1 IPS
 
Object Detection (I8)
52% 409
14.4 IPS
 
Face Detection (F32)
100% 394
4.52 IPS
 
Face Detection (F16)
100% 360
4.13 IPS
 
Face Detection (I8)
75% 411
4.72 IPS
 
Text Classification (F32)
100% 413
163.4 IPS
 
Text Classification (F16)
100% 413
163.3 IPS
 
Machine Translation (F32)
100% 385
59.3 IPS
 
Machine Translation (F16)
100% 396
61.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download