Geekbench ML Score

363
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 06:19 AM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPad Pro (9.7-inch)
Model IDiPad6,3
Motherboard J127AP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.92 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 317
34.0 IPS
 
Image Classification (F16)
100% 287
30.8 IPS
 
Image Classification (I8)
81% 233
25.0 IPS
 
Image Segmentation (F32)
100% 636
3.93 IPS
 
Image Segmentation (F16)
100% 636
3.93 IPS
 
Image Segmentation (I8)
89% 436
2.69 IPS
 
Pose Estimation (F32)
100% 611
2.47 IPS
 
Pose Estimation (F16)
100% 620
2.51 IPS
 
Pose Estimation (I8)
80% 81
0.33 IPS
 
Object Detection (F32)
100% 569
20.0 IPS
 
Object Detection (F16)
100% 566
19.9 IPS
 
Object Detection (I8)
52% 333
11.7 IPS
 
Face Detection (F32)
100% 859
9.87 IPS
 
Face Detection (F16)
100% 874
10.0 IPS
 
Face Detection (I8)
75% 327
3.75 IPS
 
Text Classification (F32)
98% 82
32.5 IPS
 
Text Classification (F16)
98% 70
27.5 IPS
 
Machine Translation (F32)
100% 504
77.7 IPS
 
Machine Translation (F16)
100% 501
77.3 IPS
 

Compare

Set Baseline Geekbench 6 now available