Geekbench ML Score

2784
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 09:49 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPad13,17
Model IDiPad13,17
Motherboard J408AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 6789
727.4 IPS
 
Image Classification (F16)
100% 6795
728.0 IPS
 
Image Classification (I8)
81% 688
73.7 IPS
 
Image Segmentation (F32)
100% 2123
13.1 IPS
 
Image Segmentation (F16)
100% 2120
13.1 IPS
 
Image Segmentation (I8)
89% 1257
7.76 IPS
 
Pose Estimation (F32)
100% 19904
80.5 IPS
 
Pose Estimation (F16)
100% 19767
80.0 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 7173
251.7 IPS
 
Object Detection (F16)
100% 7166
251.5 IPS
 
Object Detection (I8)
52% 975
34.2 IPS
 
Face Detection (F32)
100% 8627
99.1 IPS
 
Face Detection (F16)
100% 8620
99.0 IPS
 
Face Detection (I8)
75% 963
11.1 IPS
 
Text Classification (F32)
100% 1204
476.4 IPS
 
Text Classification (F16)
100% 1199
474.4 IPS
 
Machine Translation (F32)
100% 1796
276.7 IPS
 
Machine Translation (F16)
100% 1789
275.7 IPS
 

Compare

Set Baseline