Geekbench ML Score

338
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date June 30 2022 04:07 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 7 Plus
Model IDiPhone9,2
Motherboard D11AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 2.93 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 285
30.6 IPS
 
Image Classification (F16)
100% 277
29.7 IPS
 
Image Classification (I8)
81% 536
57.4 IPS
 
Image Segmentation (F32)
100% 483
2.99 IPS
 
Image Segmentation (F16)
100% 503
3.11 IPS
 
Image Segmentation (I8)
89% 856
5.29 IPS
 
Pose Estimation (F32)
100% 154
0.62 IPS
 
Pose Estimation (F16)
100% 131
0.53 IPS
 
Pose Estimation (I8)
80% 182
0.74 IPS
 
Object Detection (F32)
100% 380
13.3 IPS
 
Object Detection (F16)
100% 358
12.6 IPS
 
Object Detection (I8)
52% 506
17.7 IPS
 
Face Detection (F32)
100% 403
4.63 IPS
 
Face Detection (F16)
100% 329
3.78 IPS
 
Face Detection (I8)
75% 357
4.11 IPS
 
Text Classification (F32)
100% 319
126.2 IPS
 
Text Classification (F16)
100% 320
126.7 IPS
 
Machine Translation (F32)
100% 326
50.3 IPS
 
Machine Translation (F16)
100% 333
51.4 IPS
 

Compare

Set Baseline Geekbench 6 now available