User | CME |
Upload Date | August 15 2024 07:04 PM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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 | 7.44 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1467
272.9 IPS |
|
Image Classification (HP)
|
100% |
6212
1.16 KIPS |
|
Image Classification (Q)
|
99% |
6995
1.30 KIPS |
|
Image Segmentation (SP)
|
100% |
822
13.3 IPS |
|
Image Segmentation (HP)
|
100% |
5213
84.5 IPS |
|
Image Segmentation (Q)
|
100% |
5208
84.4 IPS |
|
Pose Estimation (SP)
|
100% |
7689
8.97 IPS |
|
Pose Estimation (HP)
|
100% |
87503
102.1 IPS |
|
Pose Estimation (Q)
|
94% |
131402
154.1 IPS |
|
Object Detection (SP)
|
100% |
1452
115.2 IPS |
|
Object Detection (HP)
|
100% |
8250
654.4 IPS |
|
Object Detection (Q)
|
93% |
9190
733.3 IPS |
|
Face Detection (SP)
|
100% |
2171
25.8 IPS |
|
Face Detection (HP)
|
100% |
11252
133.7 IPS |
|
Face Detection (Q)
|
100% |
12372
147.0 IPS |
|
Depth Estimation (SP)
|
100% |
4699
36.2 IPS |
|
Depth Estimation (HP)
|
99% |
42725
329.2 IPS |
|
Depth Estimation (Q)
|
97% |
47849
370.0 IPS |
|
Style Transfer (SP)
|
100% |
11937
15.3 IPS |
|
Style Transfer (HP)
|
100% |
128243
164.9 IPS |
|
Style Transfer (Q)
|
100% |
128538
165.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
3958
146.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
18489
682.7 IPS |
|
Image Super-Resolution (Q)
|
98% |
26184
970.1 IPS |
|
Text Classification (SP)
|
100% |
1768
2.36 KIPS |
|
Text Classification (HP)
|
71% |
4170
6.00 KIPS |
|
Text Classification (Q)
|
69% |
3871
5.67 KIPS |
|
Machine Translation (SP)
|
100% |
1894
32.6 IPS |
|
Machine Translation (HP)
|
100% |
2343
40.4 IPS |
|
Machine Translation (Q)
|
98% |
2346
40.5 IPS |