Geekbench ML Score

401
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 30 2022 01:46 AM
Views 1

System Information

System Information
Operating System iOS 15.7
Model iPad (7th generation)
Model IDiPad7,11
Motherboard J171AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.32 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% 276
29.6 IPS
 
Image Classification (F16)
100% 274
29.3 IPS
 
Image Classification (I8)
81% 521
55.8 IPS
 
Image Segmentation (F32)
100% 484
2.99 IPS
 
Image Segmentation (F16)
100% 469
2.89 IPS
 
Image Segmentation (I8)
89% 870
5.37 IPS
 
Pose Estimation (F32)
100% 148
0.60 IPS
 
Pose Estimation (F16)
100% 135
0.54 IPS
 
Pose Estimation (I8)
80% 173
0.70 IPS
 
Object Detection (F32)
100% 391
13.7 IPS
 
Object Detection (F16)
100% 405
14.2 IPS
 
Object Detection (I8)
52% 634
22.3 IPS
 
Face Detection (F32)
100% 523
6.01 IPS
 
Face Detection (F16)
100% 513
5.89 IPS
 
Face Detection (I8)
75% 576
6.62 IPS
 
Text Classification (F32)
100% 483
191.2 IPS
 
Text Classification (F16)
100% 520
205.6 IPS
 
Machine Translation (F32)
100% 535
82.5 IPS
 
Machine Translation (F16)
100% 538
83.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download