Upload Date | January 02 2025 02:35 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
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% |
1705
317.1 IPS |
|
Image Classification (HP)
|
100% |
10854
2.02 KIPS |
|
Image Classification (Q)
|
97% |
14968
2.79 KIPS |
|
Image Segmentation (SP)
|
100% |
1608
26.1 IPS |
|
Image Segmentation (HP)
|
100% |
15607
253.0 IPS |
|
Image Segmentation (Q)
|
99% |
20736
336.2 IPS |
|
Pose Estimation (SP)
|
100% |
7889
9.21 IPS |
|
Pose Estimation (HP)
|
100% |
106139
123.8 IPS |
|
Pose Estimation (Q)
|
95% |
203818
238.9 IPS |
|
Object Detection (SP)
|
100% |
1798
142.7 IPS |
|
Object Detection (HP)
|
100% |
13658
1.08 KIPS |
|
Object Detection (Q)
|
91% |
18922
1.51 KIPS |
|
Face Detection (SP)
|
100% |
3160
37.5 IPS |
|
Face Detection (HP)
|
100% |
33258
395.2 IPS |
|
Face Detection (Q)
|
100% |
49995
594.0 IPS |
|
Depth Estimation (SP)
|
100% |
7065
54.4 IPS |
|
Depth Estimation (HP)
|
99% |
78335
603.5 IPS |
|
Depth Estimation (Q)
|
85% |
128867
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
21032
27.0 IPS |
|
Style Transfer (HP)
|
100% |
202035
259.7 IPS |
|
Style Transfer (Q)
|
96% |
246709
318.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4944
182.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
33507
1.24 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57047
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3247
4.33 KIPS |
|
Text Classification (HP)
|
100% |
3049
4.07 KIPS |
|
Text Classification (Q)
|
93% |
2558
3.43 KIPS |
|
Machine Translation (SP)
|
100% |
3109
53.6 IPS |
|
Machine Translation (HP)
|
100% |
6037
104.0 IPS |
|
Machine Translation (Q)
|
98% |
7284
125.9 IPS |