Geekbench ML Score

233
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date June 11 2021 03:47 AM
Views 1

System Information

System Information
Operating System iOS 14.5.1
Model iPhone 7 Plus
Model IDiPhone9,4
Motherboard D111AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 2.93 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 130
13.9 IPS
 
Image Classification (F16)
100% 133
14.2 IPS
 
Image Classification (I8)
81% 264
28.3 IPS
 
Image Segmentation (F32)
100% 261
1.61 IPS
 
Image Segmentation (F16)
100% 261
1.61 IPS
 
Image Segmentation (I8)
89% 473
2.92 IPS
 
Pose Estimation (F32)
100% 83
0.33 IPS
 
Pose Estimation (F16)
100% 82
0.33 IPS
 
Pose Estimation (I8)
80% 109
0.44 IPS
 
Object Detection (F32)
100% 243
8.54 IPS
 
Object Detection (F16)
100% 242
8.50 IPS
 
Object Detection (I8)
52% 373
13.1 IPS
 
Face Detection (F32)
100% 328
3.77 IPS
 
Face Detection (F16)
100% 331
3.80 IPS
 
Face Detection (I8)
75% 357
4.10 IPS
 
Text Classification (F32)
100% 319
126.2 IPS
 
Text Classification (F16)
100% 320
126.6 IPS
 
Machine Translation (F32)
100% 331
51.1 IPS
 
Machine Translation (F16)
100% 327
50.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download