Geekbench ML Score

1201
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 20 2022 01:12 PM
Views 23

System Information

System Information
Operating System iOS 16.1
Model iPad14,6
Model IDiPad14,6
Motherboard J621AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.48 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.33 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1080
115.7 IPS
 
Image Classification (F16)
100% 1079
115.6 IPS
 
Image Classification (I8)
81% 566
60.7 IPS
 
Image Segmentation (F32)
100% 1427
8.81 IPS
 
Image Segmentation (F16)
100% 1450
8.96 IPS
 
Image Segmentation (I8)
89% 1723
10.6 IPS
 
Pose Estimation (F32)
100% 746
3.02 IPS
 
Pose Estimation (F16)
100% 737
2.98 IPS
 
Pose Estimation (I8)
80% 874
3.54 IPS
 
Object Detection (F32)
100% 1709
60.0 IPS
 
Object Detection (F16)
100% 1716
60.2 IPS
 
Object Detection (I8)
52% 918
32.2 IPS
 
Face Detection (F32)
100% 2021
23.2 IPS
 
Face Detection (F16)
100% 2027
23.3 IPS
 
Face Detection (I8)
75% 1030
11.8 IPS
 
Text Classification (F32)
100% 834
329.7 IPS
 
Text Classification (F16)
100% 817
323.2 IPS
 
Machine Translation (F32)
100% 1935
298.2 IPS
 
Machine Translation (F16)
100% 1934
298.0 IPS
 

Compare

Set Baseline Geekbench 6 now available