Upload Date | September 18 2024 04:35 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1413
262.8 IPS |
|
Image Classification (HP)
|
100% |
10712
1.99 KIPS |
|
Image Classification (Q)
|
97% |
15144
2.83 KIPS |
|
Image Segmentation (SP)
|
100% |
1528
24.8 IPS |
|
Image Segmentation (HP)
|
100% |
12649
205.0 IPS |
|
Image Segmentation (Q)
|
99% |
14654
237.5 IPS |
|
Pose Estimation (SP)
|
100% |
6264
7.31 IPS |
|
Pose Estimation (HP)
|
100% |
93286
108.8 IPS |
|
Pose Estimation (Q)
|
95% |
98169
115.1 IPS |
|
Object Detection (SP)
|
100% |
1176
93.3 IPS |
|
Object Detection (HP)
|
100% |
7326
581.1 IPS |
|
Object Detection (Q)
|
91% |
17100
1.37 KIPS |
|
Face Detection (SP)
|
100% |
1596
19.0 IPS |
|
Face Detection (HP)
|
100% |
21301
253.1 IPS |
|
Face Detection (Q)
|
100% |
32556
386.8 IPS |
|
Depth Estimation (SP)
|
100% |
3778
29.1 IPS |
|
Depth Estimation (HP)
|
99% |
48114
370.7 IPS |
|
Depth Estimation (Q)
|
85% |
76800
600.5 IPS |
|
Style Transfer (SP)
|
100% |
10995
14.1 IPS |
|
Style Transfer (HP)
|
100% |
185079
237.9 IPS |
|
Style Transfer (Q)
|
96% |
244972
316.1 IPS |
|
Image Super-Resolution (SP)
|
100% |
3496
129.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
33735
1.25 KIPS |
|
Image Super-Resolution (Q)
|
99% |
30335
1.12 KIPS |
|
Text Classification (SP)
|
100% |
724
966.2 IPS |
|
Text Classification (HP)
|
100% |
2326
3.10 KIPS |
|
Text Classification (Q)
|
93% |
713
956.6 IPS |
|
Machine Translation (SP)
|
100% |
1850
31.9 IPS |
|
Machine Translation (HP)
|
100% |
4200
72.4 IPS |
|
Machine Translation (Q)
|
98% |
4451
76.9 IPS |