Geekbench ML Score

399
TensorFlow Lite Core ML Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 04:13 AM
Views 1

System Information

System Information
Operating System iOS 15.5
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 Core ML

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 273
29.3 IPS
 
Image Classification (F16)
100% 224
23.9 IPS
 
Image Classification (I8)
81% 320
34.3 IPS
 
Image Segmentation (F32)
100% 649
4.01 IPS
 
Image Segmentation (F16)
100% 633
3.91 IPS
 
Image Segmentation (I8)
89% 586
3.62 IPS
 
Pose Estimation (F32)
100% 441
1.79 IPS
 
Pose Estimation (F16)
100% 446
1.80 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 629
22.1 IPS
 
Object Detection (F16)
100% 461
16.2 IPS
 
Object Detection (I8)
52% 456
16.0 IPS
 
Face Detection (F32)
100% 682
7.83 IPS
 
Face Detection (F16)
100% 798
9.17 IPS
 
Face Detection (I8)
75% 416
4.78 IPS
 
Text Classification (F32)
98% 136
53.7 IPS
 
Text Classification (F16)
98% 136
53.6 IPS
 
Machine Translation (F32)
100% 615
94.8 IPS
 
Machine Translation (F16)
100% 681
105.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download