User | M91 |
Upload Date | June 13 2025 09:53 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 19.0 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
CPU Information | |
---|---|
Name | Apple A17 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.78 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1666
309.8 IPS |
|
Image Classification (HP)
|
100% |
10822
2.01 KIPS |
|
Image Classification (Q)
|
97% |
15640
2.92 KIPS |
|
Image Segmentation (SP)
|
100% |
1612
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
16611
269.3 IPS |
|
Image Segmentation (Q)
|
99% |
21322
345.6 IPS |
|
Pose Estimation (SP)
|
100% |
7861
9.17 IPS |
|
Pose Estimation (HP)
|
100% |
106905
124.7 IPS |
|
Pose Estimation (Q)
|
95% |
207811
243.6 IPS |
|
Object Detection (SP)
|
100% |
1764
139.9 IPS |
|
Object Detection (HP)
|
100% |
13864
1.10 KIPS |
|
Object Detection (Q)
|
91% |
17373
1.39 KIPS |
|
Face Detection (SP)
|
100% |
3246
38.6 IPS |
|
Face Detection (HP)
|
100% |
34473
409.6 IPS |
|
Face Detection (Q)
|
100% |
47210
561.0 IPS |
|
Depth Estimation (SP)
|
100% |
7026
54.1 IPS |
|
Depth Estimation (HP)
|
99% |
77944
600.5 IPS |
|
Depth Estimation (Q)
|
85% |
124350
972.2 IPS |
|
Style Transfer (SP)
|
100% |
21661
27.8 IPS |
|
Style Transfer (HP)
|
100% |
206300
265.2 IPS |
|
Style Transfer (Q)
|
96% |
252672
326.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
4927
181.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
36758
1.36 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59266
2.19 KIPS |
|
Text Classification (SP)
|
100% |
2994
4.00 KIPS |
|
Text Classification (HP)
|
100% |
5076
6.78 KIPS |
|
Text Classification (Q)
|
93% |
5094
6.84 KIPS |
|
Machine Translation (SP)
|
100% |
3230
55.6 IPS |
|
Machine Translation (HP)
|
100% |
8121
139.9 IPS |
|
Machine Translation (Q)
|
98% |
9428
162.9 IPS |