Geekbench ML Score

1037
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 06:39 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 1.67 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 835
89.5 IPS
 
Image Classification (F16)
100% 814
87.2 IPS
 
Image Classification (I8)
81% 449
48.1 IPS
 
Image Segmentation (F32)
100% 1254
7.74 IPS
 
Image Segmentation (F16)
100% 1231
7.60 IPS
 
Image Segmentation (I8)
89% 1480
9.14 IPS
 
Pose Estimation (F32)
100% 456
1.84 IPS
 
Pose Estimation (F16)
100% 466
1.88 IPS
 
Pose Estimation (I8)
80% 538
2.18 IPS
 
Object Detection (F32)
100% 1230
43.2 IPS
 
Object Detection (F16)
100% 1233
43.3 IPS
 
Object Detection (I8)
52% 762
26.7 IPS
 
Face Detection (F32)
100% 1513
17.4 IPS
 
Face Detection (F16)
100% 1497
17.2 IPS
 
Face Detection (I8)
75% 866
9.95 IPS
 
Text Classification (F32)
100% 1478
584.7 IPS
 
Text Classification (F16)
100% 1453
574.7 IPS
 
Machine Translation (F32)
100% 2253
347.3 IPS
 
Machine Translation (F16)
100% 2297
354.1 IPS
 

Compare

Set Baseline