Geekbench ML Score

723
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:33 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
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

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 545
58.4 IPS
 
Image Classification (F16)
100% 532
57.0 IPS
 
Image Classification (I8)
81% 324
34.7 IPS
 
Image Segmentation (F32)
100% 876
5.41 IPS
 
Image Segmentation (F16)
100% 859
5.31 IPS
 
Image Segmentation (I8)
89% 1118
6.91 IPS
 
Pose Estimation (F32)
100% 277
1.12 IPS
 
Pose Estimation (F16)
100% 273
1.10 IPS
 
Pose Estimation (I8)
80% 331
1.34 IPS
 
Object Detection (F32)
100% 777
27.3 IPS
 
Object Detection (F16)
100% 775
27.2 IPS
 
Object Detection (I8)
52% 605
21.2 IPS
 
Face Detection (F32)
100% 987
11.3 IPS
 
Face Detection (F16)
100% 978
11.2 IPS
 
Face Detection (I8)
75% 722
8.29 IPS
 
Text Classification (F32)
100% 1761
696.4 IPS
 
Text Classification (F16)
100% 1722
681.2 IPS
 
Machine Translation (F32)
100% 1191
183.5 IPS
 
Machine Translation (F16)
100% 1189
183.2 IPS
 

Compare

Set Baseline