Upload Date | January 05 2025 06:26 PM |
Views | 1 |
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% |
1432
266.4 IPS |
|
Image Classification (HP)
|
100% |
10114
1.88 KIPS |
|
Image Classification (Q)
|
97% |
13048
2.43 KIPS |
|
Image Segmentation (SP)
|
100% |
1484
24.1 IPS |
|
Image Segmentation (HP)
|
100% |
14286
231.6 IPS |
|
Image Segmentation (Q)
|
99% |
18155
294.3 IPS |
|
Pose Estimation (SP)
|
100% |
6256
7.30 IPS |
|
Pose Estimation (HP)
|
100% |
96954
113.1 IPS |
|
Pose Estimation (Q)
|
95% |
102097
119.7 IPS |
|
Object Detection (SP)
|
100% |
1568
124.4 IPS |
|
Object Detection (HP)
|
100% |
13252
1.05 KIPS |
|
Object Detection (Q)
|
91% |
15176
1.21 KIPS |
|
Face Detection (SP)
|
100% |
3259
38.7 IPS |
|
Face Detection (HP)
|
100% |
30606
363.7 IPS |
|
Face Detection (Q)
|
100% |
39883
473.9 IPS |
|
Depth Estimation (SP)
|
100% |
6081
46.9 IPS |
|
Depth Estimation (HP)
|
99% |
76240
587.4 IPS |
|
Depth Estimation (Q)
|
85% |
97164
759.7 IPS |
|
Style Transfer (SP)
|
100% |
14742
19.0 IPS |
|
Style Transfer (HP)
|
100% |
171180
220.1 IPS |
|
Style Transfer (Q)
|
96% |
172281
222.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4176
154.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
32734
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37133
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2620
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2040
2.72 KIPS |
|
Text Classification (Q)
|
93% |
2876
3.86 KIPS |
|
Machine Translation (SP)
|
100% |
3563
61.4 IPS |
|
Machine Translation (HP)
|
100% |
7253
124.9 IPS |
|
Machine Translation (Q)
|
98% |
8088
139.8 IPS |