User | M91 |
Upload Date | December 29 2024 12:50 PM |
Views | 2 |
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% |
1982
368.6 IPS |
|
Image Classification (HP)
|
100% |
15255
2.84 KIPS |
|
Image Classification (Q)
|
97% |
19514
3.64 KIPS |
|
Image Segmentation (SP)
|
100% |
1906
30.9 IPS |
|
Image Segmentation (HP)
|
100% |
18302
296.7 IPS |
|
Image Segmentation (Q)
|
99% |
24039
389.7 IPS |
|
Pose Estimation (SP)
|
100% |
8419
9.82 IPS |
|
Pose Estimation (HP)
|
100% |
151646
176.9 IPS |
|
Pose Estimation (Q)
|
95% |
293300
343.8 IPS |
|
Object Detection (SP)
|
100% |
2171
172.2 IPS |
|
Object Detection (HP)
|
100% |
16217
1.29 KIPS |
|
Object Detection (Q)
|
91% |
22299
1.78 KIPS |
|
Face Detection (SP)
|
100% |
3524
41.9 IPS |
|
Face Detection (HP)
|
100% |
41265
490.3 IPS |
|
Face Detection (Q)
|
100% |
58437
694.4 IPS |
|
Depth Estimation (SP)
|
100% |
7773
59.9 IPS |
|
Depth Estimation (HP)
|
99% |
95124
732.9 IPS |
|
Depth Estimation (Q)
|
85% |
160422
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
23537
30.3 IPS |
|
Style Transfer (HP)
|
100% |
246215
316.5 IPS |
|
Style Transfer (Q)
|
96% |
306076
395.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
5362
198.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
51075
1.89 KIPS |
|
Image Super-Resolution (Q)
|
99% |
83738
3.09 KIPS |
|
Text Classification (SP)
|
100% |
3421
4.57 KIPS |
|
Text Classification (HP)
|
100% |
4356
5.81 KIPS |
|
Text Classification (Q)
|
93% |
4342
5.83 KIPS |
|
Machine Translation (SP)
|
100% |
3803
65.5 IPS |
|
Machine Translation (HP)
|
100% |
9752
168.0 IPS |
|
Machine Translation (Q)
|
98% |
11375
196.6 IPS |