Geekbench ML Score

1242
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 05 2022 03:34 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad14,5
Model IDiPad14,5
Motherboard J620AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.46 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% 1069
114.5 IPS
 
Image Classification (F16)
100% 1069
114.6 IPS
 
Image Classification (I8)
81% 721
77.2 IPS
 
Image Segmentation (F32)
100% 1454
8.98 IPS
 
Image Segmentation (F16)
100% 1439
8.89 IPS
 
Image Segmentation (I8)
89% 1812
11.2 IPS
 
Pose Estimation (F32)
100% 745
3.02 IPS
 
Pose Estimation (F16)
100% 755
3.05 IPS
 
Pose Estimation (I8)
80% 882
3.57 IPS
 
Object Detection (F32)
100% 1690
59.3 IPS
 
Object Detection (F16)
100% 1681
59.0 IPS
 
Object Detection (I8)
52% 1082
38.0 IPS
 
Face Detection (F32)
100% 1940
22.3 IPS
 
Face Detection (F16)
100% 1918
22.0 IPS
 
Face Detection (I8)
75% 1232
14.1 IPS
 
Text Classification (F32)
100% 948
375.1 IPS
 
Text Classification (F16)
100% 849
335.9 IPS
 
Machine Translation (F32)
100% 1875
289.0 IPS
 
Machine Translation (F16)
100% 1882
290.0 IPS
 

Compare

Set Baseline Geekbench 6 now available