Geekbench ML Score

371
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:16 PM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPhone 7
Model IDiPhone9,3
Motherboard D101AP
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 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 284
30.5 IPS
 
Image Classification (F16)
100% 267
28.6 IPS
 
Image Classification (I8)
81% 534
57.2 IPS
 
Image Segmentation (F32)
100% 492
3.04 IPS
 
Image Segmentation (F16)
100% 490
3.03 IPS
 
Image Segmentation (I8)
89% 929
5.74 IPS
 
Pose Estimation (F32)
100% 150
0.61 IPS
 
Pose Estimation (F16)
100% 143
0.58 IPS
 
Pose Estimation (I8)
80% 171
0.69 IPS
 
Object Detection (F32)
100% 416
14.6 IPS
 
Object Detection (F16)
100% 393
13.8 IPS
 
Object Detection (I8)
52% 577
20.2 IPS
 
Face Detection (F32)
100% 448
5.15 IPS
 
Face Detection (F16)
100% 484
5.56 IPS
 
Face Detection (I8)
75% 494
5.68 IPS
 
Text Classification (F32)
100% 374
147.8 IPS
 
Text Classification (F16)
100% 370
146.5 IPS
 
Machine Translation (F32)
100% 388
59.7 IPS
 
Machine Translation (F16)
100% 370
57.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download