Upload Date | September 17 2024 08:34 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% |
1683
313.1 IPS |
|
Image Classification (HP)
|
100% |
11359
2.11 KIPS |
|
Image Classification (Q)
|
97% |
14918
2.78 KIPS |
|
Image Segmentation (SP)
|
100% |
1603
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
12977
210.4 IPS |
|
Image Segmentation (Q)
|
99% |
16089
260.8 IPS |
|
Pose Estimation (SP)
|
100% |
7366
8.60 IPS |
|
Pose Estimation (HP)
|
100% |
103750
121.1 IPS |
|
Pose Estimation (Q)
|
95% |
202051
236.8 IPS |
|
Object Detection (SP)
|
100% |
1744
138.3 IPS |
|
Object Detection (HP)
|
100% |
13453
1.07 KIPS |
|
Object Detection (Q)
|
91% |
18621
1.49 KIPS |
|
Face Detection (SP)
|
100% |
3182
37.8 IPS |
|
Face Detection (HP)
|
100% |
33698
400.4 IPS |
|
Face Detection (Q)
|
100% |
49429
587.3 IPS |
|
Depth Estimation (SP)
|
100% |
6892
53.1 IPS |
|
Depth Estimation (HP)
|
99% |
78421
604.2 IPS |
|
Depth Estimation (Q)
|
85% |
128842
1.01 KIPS |
|
Style Transfer (SP)
|
100% |
19945
25.6 IPS |
|
Style Transfer (HP)
|
100% |
201817
259.4 IPS |
|
Style Transfer (Q)
|
96% |
248098
320.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4697
173.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34367
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57678
2.13 KIPS |
|
Text Classification (SP)
|
100% |
3201
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3098
4.14 KIPS |
|
Text Classification (Q)
|
93% |
3288
4.41 KIPS |
|
Machine Translation (SP)
|
100% |
3117
53.7 IPS |
|
Machine Translation (HP)
|
100% |
6109
105.2 IPS |
|
Machine Translation (Q)
|
98% |
7240
125.1 IPS |