Geekbench ML Score

418
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date July 22 2021 09:04 AM
Views 1

System Information

System Information
Operating System iOS 14.7
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.70 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 321
34.4 IPS
 
Image Classification (F16)
100% 320
34.3 IPS
 
Image Classification (I8)
81% 274
29.4 IPS
 
Image Segmentation (F32)
100% 536
3.31 IPS
 
Image Segmentation (F16)
100% 535
3.30 IPS
 
Image Segmentation (I8)
89% 781
4.82 IPS
 
Pose Estimation (F32)
100% 144
0.58 IPS
 
Pose Estimation (F16)
100% 144
0.58 IPS
 
Pose Estimation (I8)
80% 192
0.78 IPS
 
Object Detection (F32)
100% 468
16.4 IPS
 
Object Detection (F16)
100% 469
16.5 IPS
 
Object Detection (I8)
52% 486
17.0 IPS
 
Face Detection (F32)
100% 587
6.74 IPS
 
Face Detection (F16)
100% 588
6.76 IPS
 
Face Detection (I8)
75% 527
6.06 IPS
 
Text Classification (F32)
100% 529
209.2 IPS
 
Text Classification (F16)
100% 529
209.1 IPS
 
Machine Translation (F32)
100% 687
105.9 IPS
 
Machine Translation (F16)
100% 687
105.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download