User | justintea |
Upload Date | December 14 2024 02:53 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 15 |
Model ID | iPhone15,4 |
Motherboard | D37AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1447
269.1 IPS |
|
Image Classification (HP)
|
100% |
10894
2.03 KIPS |
|
Image Classification (Q)
|
97% |
12940
2.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1452
23.5 IPS |
|
Image Segmentation (HP)
|
100% |
13562
219.8 IPS |
|
Image Segmentation (Q)
|
99% |
10086
163.5 IPS |
|
Pose Estimation (SP)
|
100% |
3084
3.60 IPS |
|
Pose Estimation (HP)
|
100% |
44159
51.5 IPS |
|
Pose Estimation (Q)
|
95% |
44824
52.5 IPS |
|
Object Detection (SP)
|
100% |
677
53.7 IPS |
|
Object Detection (HP)
|
100% |
6975
553.3 IPS |
|
Object Detection (Q)
|
91% |
7921
632.9 IPS |
|
Face Detection (SP)
|
100% |
1582
18.8 IPS |
|
Face Detection (HP)
|
100% |
14689
174.5 IPS |
|
Face Detection (Q)
|
100% |
18550
220.4 IPS |
|
Depth Estimation (SP)
|
100% |
2686
20.7 IPS |
|
Depth Estimation (HP)
|
99% |
36310
279.8 IPS |
|
Depth Estimation (Q)
|
85% |
42675
333.7 IPS |
|
Style Transfer (SP)
|
100% |
8333
10.7 IPS |
|
Style Transfer (HP)
|
100% |
86974
111.8 IPS |
|
Style Transfer (Q)
|
96% |
85711
110.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
1885
69.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
17343
640.4 IPS |
|
Image Super-Resolution (Q)
|
99% |
20732
765.6 IPS |
|
Text Classification (SP)
|
100% |
1237
1.65 KIPS |
|
Text Classification (HP)
|
100% |
1777
2.37 KIPS |
|
Text Classification (Q)
|
93% |
2544
3.41 KIPS |
|
Machine Translation (SP)
|
100% |
1689
29.1 IPS |
|
Machine Translation (HP)
|
100% |
3853
66.4 IPS |
|
Machine Translation (Q)
|
98% |
3920
67.7 IPS |