Upload Date | April 08 2025 09:41 AM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.3.2 |
Model | iPhone 15 Pro Max |
Model ID | iPhone16,2 |
Motherboard | D84AP |
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 | 7.48 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1709
317.9 IPS |
|
Image Classification (HP)
|
100% |
10944
2.04 KIPS |
|
Image Classification (Q)
|
97% |
15083
2.81 KIPS |
|
Image Segmentation (SP)
|
100% |
1600
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15670
254.0 IPS |
|
Image Segmentation (Q)
|
99% |
20907
338.9 IPS |
|
Pose Estimation (SP)
|
100% |
7909
9.23 IPS |
|
Pose Estimation (HP)
|
100% |
106441
124.2 IPS |
|
Pose Estimation (Q)
|
95% |
204331
239.5 IPS |
|
Object Detection (SP)
|
100% |
1808
143.4 IPS |
|
Object Detection (HP)
|
100% |
13854
1.10 KIPS |
|
Object Detection (Q)
|
91% |
18687
1.49 KIPS |
|
Face Detection (SP)
|
100% |
3162
37.6 IPS |
|
Face Detection (HP)
|
100% |
34003
404.0 IPS |
|
Face Detection (Q)
|
100% |
50231
596.9 IPS |
|
Depth Estimation (SP)
|
100% |
7053
54.3 IPS |
|
Depth Estimation (HP)
|
99% |
78267
603.0 IPS |
|
Depth Estimation (Q)
|
85% |
128382
1.00 KIPS |
|
Style Transfer (SP)
|
100% |
21192
27.2 IPS |
|
Style Transfer (HP)
|
100% |
202252
260.0 IPS |
|
Style Transfer (Q)
|
96% |
246593
318.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
5038
186.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
33772
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
62296
2.30 KIPS |
|
Text Classification (SP)
|
100% |
3206
4.28 KIPS |
|
Text Classification (HP)
|
100% |
2693
3.59 KIPS |
|
Text Classification (Q)
|
93% |
1886
2.53 KIPS |
|
Machine Translation (SP)
|
100% |
3114
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6043
104.1 IPS |
|
Machine Translation (Q)
|
98% |
7236
125.0 IPS |