Geekbench ML Score

3132
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 03:47 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 Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 7569
811.0 IPS
 
Image Classification (F16)
100% 7558
809.8 IPS
 
Image Classification (I8)
81% 734
78.6 IPS
 
Image Segmentation (F32)
100% 2285
14.1 IPS
 
Image Segmentation (F16)
100% 2247
13.9 IPS
 
Image Segmentation (I8)
89% 1343
8.29 IPS
 
Pose Estimation (F32)
100% 27961
113.1 IPS
 
Pose Estimation (F16)
100% 27625
111.8 IPS
 
Pose Estimation (I8)
80% 255
1.03 IPS
 
Object Detection (F32)
100% 8719
306.0 IPS
 
Object Detection (F16)
100% 8699
305.3 IPS
 
Object Detection (I8)
52% 1051
36.9 IPS
 
Face Detection (F32)
100% 9597
110.3 IPS
 
Face Detection (F16)
100% 9603
110.3 IPS
 
Face Detection (I8)
75% 1026
11.8 IPS
 
Text Classification (F32)
100% 1313
519.5 IPS
 
Text Classification (F16)
100% 1312
518.8 IPS
 
Machine Translation (F32)
100% 1877
289.3 IPS
 
Machine Translation (F16)
100% 1902
293.1 IPS
 

Compare

Set Baseline