Geekbench ML Score

402
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 01:16 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad (6th generation)
Model IDiPad7,6
Motherboard J72bAP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.32 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework TensorFlow Lite
Backend Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 220
23.6 IPS
 
Image Classification (F16)
100% 249
26.7 IPS
 
Image Classification (I8)
81% 320
34.3 IPS
 
Image Segmentation (F32)
100% 643
3.97 IPS
 
Image Segmentation (F16)
100% 631
3.89 IPS
 
Image Segmentation (I8)
89% 590
3.64 IPS
 
Pose Estimation (F32)
100% 442
1.79 IPS
 
Pose Estimation (F16)
100% 442
1.79 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 634
22.3 IPS
 
Object Detection (F16)
100% 661
23.2 IPS
 
Object Detection (I8)
52% 459
16.1 IPS
 
Face Detection (F32)
100% 820
9.42 IPS
 
Face Detection (F16)
100% 649
7.46 IPS
 
Face Detection (I8)
75% 418
4.81 IPS
 
Text Classification (F32)
98% 142
56.1 IPS
 
Text Classification (F16)
98% 107
42.3 IPS
 
Machine Translation (F32)
100% 683
105.3 IPS
 
Machine Translation (F16)
100% 686
105.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download