User | M91 |
Upload Date | April 03 2025 12:11 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
1685
313.4 IPS |
|
Image Classification (HP)
|
100% |
11109
2.07 KIPS |
|
Image Classification (Q)
|
97% |
15164
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1600
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15867
257.2 IPS |
|
Image Segmentation (Q)
|
99% |
21324
345.7 IPS |
|
Pose Estimation (SP)
|
100% |
7725
9.01 IPS |
|
Pose Estimation (HP)
|
100% |
105568
123.2 IPS |
|
Pose Estimation (Q)
|
95% |
206303
241.8 IPS |
|
Object Detection (SP)
|
100% |
1771
140.5 IPS |
|
Object Detection (HP)
|
100% |
13853
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18955
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3177
37.8 IPS |
|
Face Detection (HP)
|
100% |
34209
406.5 IPS |
|
Face Detection (Q)
|
100% |
52001
617.9 IPS |
|
Depth Estimation (SP)
|
100% |
6896
53.1 IPS |
|
Depth Estimation (HP)
|
99% |
78733
606.6 IPS |
|
Depth Estimation (Q)
|
85% |
126279
987.3 IPS |
|
Style Transfer (SP)
|
100% |
20982
27.0 IPS |
|
Style Transfer (HP)
|
100% |
203567
261.7 IPS |
|
Style Transfer (Q)
|
96% |
248416
320.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4764
175.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34611
1.28 KIPS |
|
Image Super-Resolution (Q)
|
99% |
53842
1.99 KIPS |
|
Text Classification (SP)
|
100% |
3242
4.33 KIPS |
|
Text Classification (HP)
|
100% |
2861
3.82 KIPS |
|
Text Classification (Q)
|
93% |
3122
4.19 KIPS |
|
Machine Translation (SP)
|
100% |
3193
55.0 IPS |
|
Machine Translation (HP)
|
100% |
6560
113.0 IPS |
|
Machine Translation (Q)
|
98% |
7740
133.8 IPS |