Geekbench ML Score

624
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 12 2023 07:30 PM
Views 1

System Information

System Information
Operating System iOS 17.0
Model iPad12,1
Model IDiPad12,1
Motherboard J181AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.65 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 2.87 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 511
54.7 IPS
 
Image Classification (F16)
100% 512
54.9 IPS
 
Image Classification (I8)
81% 200
21.4 IPS
 
Image Segmentation (F32)
100% 839
5.19 IPS
 
Image Segmentation (F16)
100% 791
4.89 IPS
 
Image Segmentation (I8)
89% 1052
6.50 IPS
 
Pose Estimation (F32)
100% 135
0.55 IPS
 
Pose Estimation (F16)
100% 157
0.64 IPS
 
Pose Estimation (I8)
80% 293
1.19 IPS
 
Object Detection (F32)
100% 786
27.6 IPS
 
Object Detection (F16)
100% 775
27.2 IPS
 
Object Detection (I8)
52% 435
15.2 IPS
 
Face Detection (F32)
100% 975
11.2 IPS
 
Face Detection (F16)
100% 891
10.2 IPS
 
Face Detection (I8)
75% 705
8.10 IPS
 
Text Classification (F32)
100% 1693
669.6 IPS
 
Text Classification (F16)
100% 1575
623.1 IPS
 
Machine Translation (F32)
100% 1130
174.2 IPS
 
Machine Translation (F16)
100% 1186
182.8 IPS
 

Compare

Set Baseline Geekbench 6 now available