Upload Date | December 14 2024 10:20 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 16 Pro Max |
Model ID | iPhone17,2 |
Motherboard | D94AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.45 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1944
361.5 IPS |
|
Image Classification (HP)
|
100% |
15369
2.86 KIPS |
|
Image Classification (Q)
|
97% |
21143
3.95 KIPS |
|
Image Segmentation (SP)
|
100% |
1881
30.5 IPS |
|
Image Segmentation (HP)
|
100% |
18317
296.9 IPS |
|
Image Segmentation (Q)
|
99% |
24210
392.5 IPS |
|
Pose Estimation (SP)
|
100% |
7796
9.10 IPS |
|
Pose Estimation (HP)
|
100% |
143536
167.5 IPS |
|
Pose Estimation (Q)
|
95% |
294486
345.2 IPS |
|
Object Detection (SP)
|
100% |
2131
169.0 IPS |
|
Object Detection (HP)
|
100% |
16351
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22778
1.82 KIPS |
|
Face Detection (SP)
|
100% |
3652
43.4 IPS |
|
Face Detection (HP)
|
100% |
41196
489.5 IPS |
|
Face Detection (Q)
|
100% |
57144
679.0 IPS |
|
Depth Estimation (SP)
|
100% |
8076
62.2 IPS |
|
Depth Estimation (HP)
|
99% |
95335
734.5 IPS |
|
Depth Estimation (Q)
|
85% |
160157
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
24516
31.5 IPS |
|
Style Transfer (HP)
|
100% |
245448
315.5 IPS |
|
Style Transfer (Q)
|
96% |
301323
388.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5800
214.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
50806
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
87138
3.22 KIPS |
|
Text Classification (SP)
|
100% |
3418
4.56 KIPS |
|
Text Classification (HP)
|
100% |
4725
6.31 KIPS |
|
Text Classification (Q)
|
93% |
4901
6.58 KIPS |
|
Machine Translation (SP)
|
100% |
3795
65.4 IPS |
|
Machine Translation (HP)
|
100% |
9601
165.4 IPS |
|
Machine Translation (Q)
|
98% |
11481
198.4 IPS |