Geekbench ML Score

415
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date July 22 2021 08:54 AM
Views 3

System Information

System Information
Operating System iOS 14.7
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
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 280
30.0 IPS
 
Image Classification (F16)
100% 270
28.9 IPS
 
Image Classification (I8)
81% 538
57.6 IPS
 
Image Segmentation (F32)
100% 494
3.05 IPS
 
Image Segmentation (F16)
100% 506
3.13 IPS
 
Image Segmentation (I8)
89% 926
5.72 IPS
 
Pose Estimation (F32)
100% 146
0.59 IPS
 
Pose Estimation (F16)
100% 132
0.54 IPS
 
Pose Estimation (I8)
80% 191
0.77 IPS
 
Object Detection (F32)
100% 421
14.8 IPS
 
Object Detection (F16)
100% 431
15.1 IPS
 
Object Detection (I8)
52% 653
22.9 IPS
 
Face Detection (F32)
100% 539
6.20 IPS
 
Face Detection (F16)
100% 519
5.96 IPS
 
Face Detection (I8)
75% 597
6.86 IPS
 
Text Classification (F32)
100% 493
195.0 IPS
 
Text Classification (F16)
100% 474
187.5 IPS
 
Machine Translation (F32)
100% 597
92.0 IPS
 
Machine Translation (F16)
100% 597
92.0 IPS
 

Compare

Set Baseline Geekbench 6 now available