User | justintea |
Upload Date | January 04 2025 05:26 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.3 |
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% |
1445
268.8 IPS |
|
Image Classification (HP)
|
100% |
9858
1.83 KIPS |
|
Image Classification (Q)
|
97% |
11797
2.20 KIPS |
|
Image Segmentation (SP)
|
100% |
1534
24.9 IPS |
|
Image Segmentation (HP)
|
100% |
14260
231.2 IPS |
|
Image Segmentation (Q)
|
99% |
18010
292.0 IPS |
|
Pose Estimation (SP)
|
100% |
6388
7.45 IPS |
|
Pose Estimation (HP)
|
100% |
95835
111.8 IPS |
|
Pose Estimation (Q)
|
95% |
102001
119.6 IPS |
|
Object Detection (SP)
|
100% |
1574
124.8 IPS |
|
Object Detection (HP)
|
100% |
12588
998.5 IPS |
|
Object Detection (Q)
|
91% |
14819
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3285
39.0 IPS |
|
Face Detection (HP)
|
100% |
30965
367.9 IPS |
|
Face Detection (Q)
|
100% |
40104
476.5 IPS |
|
Depth Estimation (SP)
|
100% |
5907
45.5 IPS |
|
Depth Estimation (HP)
|
99% |
75600
582.5 IPS |
|
Depth Estimation (Q)
|
85% |
97249
760.3 IPS |
|
Style Transfer (SP)
|
100% |
11486
14.8 IPS |
|
Style Transfer (HP)
|
100% |
171889
221.0 IPS |
|
Style Transfer (Q)
|
96% |
172604
222.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4100
151.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
33430
1.23 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37198
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2683
3.58 KIPS |
|
Text Classification (HP)
|
100% |
2150
2.87 KIPS |
|
Text Classification (Q)
|
93% |
1755
2.36 KIPS |
|
Machine Translation (SP)
|
100% |
3476
59.9 IPS |
|
Machine Translation (HP)
|
100% |
7462
128.5 IPS |
|
Machine Translation (Q)
|
98% |
8364
144.5 IPS |