Geekbench ML Score

1240
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 03:44 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPad14,5
Model IDiPad14,5
Motherboard J620AP
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 7.33 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1096
117.4 IPS
 
Image Classification (F16)
100% 1074
115.0 IPS
 
Image Classification (I8)
81% 730
78.2 IPS
 
Image Segmentation (F32)
100% 1475
9.11 IPS
 
Image Segmentation (F16)
100% 1437
8.88 IPS
 
Image Segmentation (I8)
89% 1794
11.1 IPS
 
Pose Estimation (F32)
100% 748
3.03 IPS
 
Pose Estimation (F16)
100% 748
3.03 IPS
 
Pose Estimation (I8)
80% 884
3.58 IPS
 
Object Detection (F32)
100% 1711
60.1 IPS
 
Object Detection (F16)
100% 1693
59.4 IPS
 
Object Detection (I8)
52% 1052
36.9 IPS
 
Face Detection (F32)
100% 1941
22.3 IPS
 
Face Detection (F16)
100% 1953
22.4 IPS
 
Face Detection (I8)
75% 1215
14.0 IPS
 
Text Classification (F32)
100% 858
339.3 IPS
 
Text Classification (F16)
100% 861
340.6 IPS
 
Machine Translation (F32)
100% 1898
292.6 IPS
 
Machine Translation (F16)
100% 1890
291.3 IPS
 

Compare

Set Baseline