Geekbench ML Score

1004
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date April 28 2022 12:10 PM
Views 1

System Information

System Information
Operating System iOS 15.4.1
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 7.45 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 940
100.7 IPS
 
Image Classification (F16)
100% 942
100.9 IPS
 
Image Classification (I8)
81% 409
43.8 IPS
 
Image Segmentation (F32)
100% 1328
8.20 IPS
 
Image Segmentation (F16)
100% 1327
8.20 IPS
 
Image Segmentation (I8)
89% 1541
9.52 IPS
 
Pose Estimation (F32)
100% 667
2.70 IPS
 
Pose Estimation (F16)
100% 642
2.60 IPS
 
Pose Estimation (I8)
80% 798
3.23 IPS
 
Object Detection (F32)
100% 1454
51.0 IPS
 
Object Detection (F16)
100% 1458
51.2 IPS
 
Object Detection (I8)
52% 577
20.3 IPS
 
Face Detection (F32)
100% 1623
18.6 IPS
 
Face Detection (F16)
100% 1626
18.7 IPS
 
Face Detection (I8)
75% 794
9.12 IPS
 
Text Classification (F32)
100% 601
237.6 IPS
 
Text Classification (F16)
100% 610
241.4 IPS
 
Machine Translation (F32)
100% 1869
288.1 IPS
 
Machine Translation (F16)
100% 1837
283.1 IPS
 

Compare

Set Baseline Geekbench 6 now available