User | Kiruno |
Upload Date | December 31 2024 01:20 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.3 |
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% |
2003
372.5 IPS |
|
Image Classification (HP)
|
100% |
15353
2.86 KIPS |
|
Image Classification (Q)
|
97% |
20976
3.91 KIPS |
|
Image Segmentation (SP)
|
100% |
1925
31.2 IPS |
|
Image Segmentation (HP)
|
100% |
18295
296.6 IPS |
|
Image Segmentation (Q)
|
99% |
23993
389.0 IPS |
|
Pose Estimation (SP)
|
100% |
8005
9.34 IPS |
|
Pose Estimation (HP)
|
100% |
141529
165.1 IPS |
|
Pose Estimation (Q)
|
95% |
292332
342.6 IPS |
|
Object Detection (SP)
|
100% |
2068
164.0 IPS |
|
Object Detection (HP)
|
100% |
16514
1.31 KIPS |
|
Object Detection (Q)
|
91% |
22850
1.83 KIPS |
|
Face Detection (SP)
|
100% |
3335
39.6 IPS |
|
Face Detection (HP)
|
100% |
41180
489.3 IPS |
|
Face Detection (Q)
|
100% |
58104
690.4 IPS |
|
Depth Estimation (SP)
|
100% |
7231
55.7 IPS |
|
Depth Estimation (HP)
|
99% |
94460
727.8 IPS |
|
Depth Estimation (Q)
|
85% |
160815
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
22229
28.6 IPS |
|
Style Transfer (HP)
|
100% |
244744
314.6 IPS |
|
Style Transfer (Q)
|
96% |
301458
389.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5306
195.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
50400
1.86 KIPS |
|
Image Super-Resolution (Q)
|
99% |
81933
3.03 KIPS |
|
Text Classification (SP)
|
100% |
3411
4.55 KIPS |
|
Text Classification (HP)
|
100% |
4878
6.51 KIPS |
|
Text Classification (Q)
|
93% |
4547
6.10 KIPS |
|
Machine Translation (SP)
|
100% |
3759
64.7 IPS |
|
Machine Translation (HP)
|
100% |
9334
160.8 IPS |
|
Machine Translation (Q)
|
98% |
11343
196.0 IPS |