| User | kelevra |
| Upload Date | December 07 2024 08:24 AM |
| Views | 7 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A18 Pro |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| 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 | 7.47 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1987
369.5 IPS |
|
|
Image Classification (HP)
|
100% |
3372
627.2 IPS |
|
|
Image Classification (Q)
|
96% |
2266
423.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1901
30.8 IPS |
|
|
Image Segmentation (HP)
|
100% |
2889
46.8 IPS |
|
|
Image Segmentation (Q)
|
99% |
3361
54.5 IPS |
|
|
Pose Estimation (SP)
|
100% |
8551
9.98 IPS |
|
|
Pose Estimation (HP)
|
100% |
17496
20.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
14488
17.0 IPS |
|
|
Object Detection (SP)
|
100% |
2063
163.7 IPS |
|
|
Object Detection (HP)
|
97% |
3769
300.0 IPS |
|
|
Object Detection (Q)
|
94% |
2644
210.7 IPS |
|
|
Face Detection (SP)
|
100% |
3487
41.4 IPS |
|
|
Face Detection (HP)
|
100% |
7305
86.8 IPS |
|
|
Face Detection (Q)
|
100% |
4066
48.3 IPS |
|
|
Depth Estimation (SP)
|
100% |
7398
57.0 IPS |
|
|
Depth Estimation (HP)
|
97% |
13746
106.3 IPS |
|
|
Depth Estimation (Q)
|
86% |
9453
73.8 IPS |
|
|
Style Transfer (SP)
|
100% |
22874
29.4 IPS |
|
|
Style Transfer (HP)
|
100% |
35767
46.0 IPS |
|
|
Style Transfer (Q)
|
96% |
29156
37.6 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5388
199.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6903
254.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
4875
180.0 IPS |
|
|
Text Classification (SP)
|
100% |
3428
4.58 KIPS |
|
|
Text Classification (HP)
|
100% |
5885
7.86 KIPS |
|
|
Text Classification (Q)
|
93% |
5832
7.83 KIPS |
|
|
Machine Translation (SP)
|
100% |
3769
64.9 IPS |
|
|
Machine Translation (HP)
|
98% |
6993
120.8 IPS |
|
|
Machine Translation (Q)
|
98% |
6944
120.0 IPS |