Geekbench ML Score

328
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 04:38 PM
Views 1

System Information

System Information
Operating System iOS 14.7.1
Model iPhone 7
Model IDiPhone9,3
Motherboard D101AP
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 1.95 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 279
29.8 IPS
 
Image Classification (F16)
100% 253
27.2 IPS
 
Image Classification (I8)
81% 463
49.6 IPS
 
Image Segmentation (F32)
100% 465
2.87 IPS
 
Image Segmentation (F16)
100% 479
2.96 IPS
 
Image Segmentation (I8)
89% 825
5.10 IPS
 
Pose Estimation (F32)
100% 143
0.58 IPS
 
Pose Estimation (F16)
100% 132
0.53 IPS
 
Pose Estimation (I8)
80% 157
0.63 IPS
 
Object Detection (F32)
100% 356
12.5 IPS
 
Object Detection (F16)
100% 334
11.7 IPS
 
Object Detection (I8)
52% 501
17.6 IPS
 
Face Detection (F32)
100% 406
4.67 IPS
 
Face Detection (F16)
100% 397
4.56 IPS
 
Face Detection (I8)
75% 351
4.04 IPS
 
Text Classification (F32)
100% 317
125.4 IPS
 
Text Classification (F16)
100% 312
123.4 IPS
 
Machine Translation (F32)
100% 333
51.3 IPS
 
Machine Translation (F16)
100% 332
51.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download