Upload Date | May 07 2025 07:13 AM |
Views | 6 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.4.1 |
Model | iPhone SE (3rd generation) |
Model ID | iPhone14,6 |
Motherboard | D49AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 3.80 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1344
249.9 IPS |
|
Image Classification (HP)
|
100% |
8213
1.53 KIPS |
|
Image Classification (Q)
|
96% |
10555
1.97 KIPS |
|
Image Segmentation (SP)
|
100% |
1314
21.3 IPS |
|
Image Segmentation (HP)
|
100% |
13339
216.2 IPS |
|
Image Segmentation (Q)
|
99% |
13514
219.1 IPS |
|
Pose Estimation (SP)
|
100% |
5951
6.94 IPS |
|
Pose Estimation (HP)
|
100% |
88153
102.9 IPS |
|
Pose Estimation (Q)
|
95% |
96543
113.2 IPS |
|
Object Detection (SP)
|
100% |
1402
111.2 IPS |
|
Object Detection (HP)
|
99% |
10976
873.1 IPS |
|
Object Detection (Q)
|
91% |
12146
970.5 IPS |
|
Face Detection (SP)
|
100% |
2651
31.5 IPS |
|
Face Detection (HP)
|
100% |
28490
338.5 IPS |
|
Face Detection (Q)
|
100% |
36328
431.7 IPS |
|
Depth Estimation (SP)
|
100% |
5171
39.8 IPS |
|
Depth Estimation (HP)
|
99% |
56106
432.3 IPS |
|
Depth Estimation (Q)
|
85% |
75178
587.5 IPS |
|
Style Transfer (SP)
|
100% |
15341
19.7 IPS |
|
Style Transfer (HP)
|
100% |
140637
180.8 IPS |
|
Style Transfer (Q)
|
96% |
142331
183.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
3830
141.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
26293
970.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
27848
1.03 KIPS |
|
Text Classification (SP)
|
100% |
2438
3.25 KIPS |
|
Text Classification (HP)
|
100% |
2445
3.26 KIPS |
|
Text Classification (Q)
|
93% |
2517
3.38 KIPS |
|
Machine Translation (SP)
|
100% |
3672
63.2 IPS |
|
Machine Translation (HP)
|
100% |
6263
107.9 IPS |
|
Machine Translation (Q)
|
98% |
7076
122.3 IPS |