Geekbench ML Score

635
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 05 2021 04:46 PM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPhone 11
Model IDiPhone12,1
Motherboard N104AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.76 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 367
39.3 IPS
 
Image Classification (F16)
100% 384
41.1 IPS
 
Image Classification (I8)
81% 301
32.2 IPS
 
Image Segmentation (F32)
100% 742
4.58 IPS
 
Image Segmentation (F16)
100% 728
4.50 IPS
 
Image Segmentation (I8)
89% 1074
6.63 IPS
 
Pose Estimation (F32)
100% 184
0.74 IPS
 
Pose Estimation (F16)
100% 182
0.74 IPS
 
Pose Estimation (I8)
80% 301
1.22 IPS
 
Object Detection (F32)
100% 782
27.4 IPS
 
Object Detection (F16)
100% 774
27.2 IPS
 
Object Detection (I8)
52% 590
20.7 IPS
 
Face Detection (F32)
100% 781
8.97 IPS
 
Face Detection (F16)
100% 767
8.81 IPS
 
Face Detection (I8)
75% 680
7.81 IPS
 
Text Classification (F32)
100% 1833
725.2 IPS
 
Text Classification (F16)
100% 1914
757.1 IPS
 
Machine Translation (F32)
100% 1201
185.0 IPS
 
Machine Translation (F16)
100% 1196
184.3 IPS
 

Compare

Set Baseline Geekbench 6 now available