Geekbench ML Score

1381
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 06:31 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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1269
136.0 IPS
 
Image Classification (F16)
100% 1564
167.6 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 3454
21.3 IPS
 
Image Segmentation (F16)
100% 5360
33.1 IPS
 
Image Segmentation (I8)
89% 836
5.17 IPS
 
Pose Estimation (F32)
100% 1419
5.74 IPS
 
Pose Estimation (F16)
100% 4419
17.9 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
100% 1516
53.2 IPS
 
Object Detection (F16)
99% 1813
63.6 IPS
 
Object Detection (I8)
52% 635
22.3 IPS
 
Face Detection (F32)
100% 3604
41.4 IPS
 
Face Detection (F16)
97% 5329
61.2 IPS
 
Face Detection (I8)
75% 636
7.30 IPS
 
Text Classification (F32)
100% 957
378.4 IPS
 
Text Classification (F16)
98% 1203
475.7 IPS
 
Machine Translation (F32)
100% 1194
184.0 IPS
 
Machine Translation (F16)
100% 1190
183.4 IPS
 

Compare

Set Baseline