Geekbench ML Score

565
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 06:54 AM
Views 1

System Information

System Information
Operating System iOS 14.7.1
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% 463
49.6 IPS
 
Image Classification (F16)
100% 464
49.7 IPS
 
Image Classification (I8)
81% 272
29.2 IPS
 
Image Segmentation (F32)
100% 780
4.82 IPS
 
Image Segmentation (F16)
100% 766
4.73 IPS
 
Image Segmentation (I8)
89% 983
6.07 IPS
 
Pose Estimation (F32)
100% 232
0.94 IPS
 
Pose Estimation (F16)
100% 155
0.63 IPS
 
Pose Estimation (I8)
80% 254
1.03 IPS
 
Object Detection (F32)
100% 673
23.6 IPS
 
Object Detection (F16)
100% 670
23.5 IPS
 
Object Detection (I8)
52% 536
18.8 IPS
 
Face Detection (F32)
100% 827
9.50 IPS
 
Face Detection (F16)
100% 829
9.53 IPS
 
Face Detection (I8)
75% 624
7.16 IPS
 
Text Classification (F32)
100% 780
308.7 IPS
 
Text Classification (F16)
100% 786
310.8 IPS
 
Machine Translation (F32)
100% 993
153.0 IPS
 
Machine Translation (F16)
100% 994
153.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download