| Upload Date | August 15 2024 08:08 PM |
| Views | 3 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A17 Pro |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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 | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1901
353.6 IPS |
|
|
Image Classification (HP)
|
100% |
2061
383.2 IPS |
|
|
Image Classification (Q)
|
99% |
2033
379.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
3101
50.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
3940
63.9 IPS |
|
|
Image Segmentation (Q)
|
100% |
3891
63.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
15017
17.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
15997
18.7 IPS |
|
|
Pose Estimation (Q)
|
96% |
14659
17.2 IPS |
|
|
Object Detection (SP)
|
100% |
2487
197.3 IPS |
|
|
Object Detection (HP)
|
100% |
2828
224.3 IPS |
|
|
Object Detection (Q)
|
92% |
2257
180.2 IPS |
|
|
Face Detection (SP)
|
100% |
6330
75.2 IPS |
|
|
Face Detection (HP)
|
100% |
8502
101.0 IPS |
|
|
Face Detection (Q)
|
100% |
6110
72.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
11900
91.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
12681
97.7 IPS |
|
|
Depth Estimation (Q)
|
97% |
13144
101.6 IPS |
|
|
Style Transfer (SP)
|
100% |
29720
38.2 IPS |
|
|
Style Transfer (HP)
|
100% |
34940
44.9 IPS |
|
|
Style Transfer (Q)
|
100% |
34850
44.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
6288
232.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6952
256.7 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
5612
207.9 IPS |
|
|
Text Classification (SP)
|
100% |
491
655.6 IPS |
|
|
Text Classification (HP)
|
100% |
523
698.2 IPS |
|
|
Text Classification (Q)
|
93% |
326
438.2 IPS |
|
|
Machine Translation (SP)
|
100% |
1096
18.9 IPS |
|
|
Machine Translation (HP)
|
100% |
1208
20.8 IPS |
|
|
Machine Translation (Q)
|
98% |
1578
27.3 IPS |