Geekbench ML Score

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

Result Information

Upload Date February 22 2023 01:21 PM
Views 4

System Information

System Information
Operating System iOS 16.3.1
Model iPad13,16
Model IDiPad13,16
Motherboard J407AP
CPU Information
Name ARM
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.20 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 CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 949
101.7 IPS
 
Image Classification (F16)
100% 930
99.7 IPS
 
Image Classification (I8)
81% 408
43.8 IPS
 
Image Segmentation (F32)
100% 1338
8.27 IPS
 
Image Segmentation (F16)
100% 1342
8.29 IPS
 
Image Segmentation (I8)
89% 1527
9.43 IPS
 
Pose Estimation (F32)
100% 666
2.70 IPS
 
Pose Estimation (F16)
100% 664
2.69 IPS
 
Pose Estimation (I8)
80% 799
3.23 IPS
 
Object Detection (F32)
100% 1418
49.8 IPS
 
Object Detection (F16)
100% 1423
50.0 IPS
 
Object Detection (I8)
52% 577
20.3 IPS
 
Face Detection (F32)
100% 1631
18.7 IPS
 
Face Detection (F16)
100% 1628
18.7 IPS
 
Face Detection (I8)
75% 800
9.20 IPS
 
Text Classification (F32)
100% 624
246.7 IPS
 
Text Classification (F16)
100% 615
243.3 IPS
 
Machine Translation (F32)
100% 1808
278.6 IPS
 
Machine Translation (F16)
100% 1804
278.1 IPS
 

Compare

Set Baseline Geekbench 6 now available