Upload Date | January 05 2025 06:30 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% |
1428
265.5 IPS |
|
Image Classification (HP)
|
100% |
10251
1.91 KIPS |
|
Image Classification (Q)
|
97% |
12641
2.36 KIPS |
|
Image Segmentation (SP)
|
100% |
1471
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
13862
224.7 IPS |
|
Image Segmentation (Q)
|
99% |
18054
292.7 IPS |
|
Pose Estimation (SP)
|
100% |
6712
7.83 IPS |
|
Pose Estimation (HP)
|
100% |
95056
110.9 IPS |
|
Pose Estimation (Q)
|
95% |
101757
119.3 IPS |
|
Object Detection (SP)
|
100% |
1609
127.6 IPS |
|
Object Detection (HP)
|
100% |
13098
1.04 KIPS |
|
Object Detection (Q)
|
91% |
14975
1.20 KIPS |
|
Face Detection (SP)
|
100% |
3263
38.8 IPS |
|
Face Detection (HP)
|
100% |
30790
365.9 IPS |
|
Face Detection (Q)
|
100% |
39830
473.3 IPS |
|
Depth Estimation (SP)
|
100% |
6135
47.3 IPS |
|
Depth Estimation (HP)
|
99% |
75010
577.9 IPS |
|
Depth Estimation (Q)
|
85% |
95154
744.0 IPS |
|
Style Transfer (SP)
|
100% |
18469
23.7 IPS |
|
Style Transfer (HP)
|
100% |
171369
220.3 IPS |
|
Style Transfer (Q)
|
96% |
173387
223.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4127
152.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
32712
1.21 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37036
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2620
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2037
2.72 KIPS |
|
Text Classification (Q)
|
93% |
1858
2.49 KIPS |
|
Machine Translation (SP)
|
100% |
3400
58.6 IPS |
|
Machine Translation (HP)
|
100% |
7342
126.5 IPS |
|
Machine Translation (Q)
|
98% |
8168
141.1 IPS |