User | mermi |
Upload Date | November 03 2024 03:27 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.7.1 |
Model | iPhone 15 Pro |
Model ID | iPhone16,1 |
Motherboard | D83AP |
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 | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1451
269.8 IPS |
|
Image Classification (HP)
|
100% |
6267
1.17 KIPS |
|
Image Classification (Q)
|
97% |
7568
1.41 KIPS |
|
Image Segmentation (SP)
|
100% |
820
13.3 IPS |
|
Image Segmentation (HP)
|
100% |
5249
85.1 IPS |
|
Image Segmentation (Q)
|
99% |
9901
160.5 IPS |
|
Pose Estimation (SP)
|
100% |
7617
8.89 IPS |
|
Pose Estimation (HP)
|
100% |
87341
101.9 IPS |
|
Pose Estimation (Q)
|
95% |
151858
178.0 IPS |
|
Object Detection (SP)
|
100% |
1487
117.9 IPS |
|
Object Detection (HP)
|
100% |
8124
644.4 IPS |
|
Object Detection (Q)
|
93% |
10018
799.3 IPS |
|
Face Detection (SP)
|
100% |
2316
27.5 IPS |
|
Face Detection (HP)
|
100% |
11203
133.1 IPS |
|
Face Detection (Q)
|
100% |
13245
157.4 IPS |
|
Depth Estimation (SP)
|
100% |
4682
36.1 IPS |
|
Depth Estimation (HP)
|
99% |
43434
334.6 IPS |
|
Depth Estimation (Q)
|
85% |
63089
493.3 IPS |
|
Style Transfer (SP)
|
100% |
12315
15.8 IPS |
|
Style Transfer (HP)
|
100% |
128388
165.0 IPS |
|
Style Transfer (Q)
|
96% |
137793
177.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
4115
151.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
18309
676.1 IPS |
|
Image Super-Resolution (Q)
|
99% |
26114
964.3 IPS |
|
Text Classification (SP)
|
100% |
1830
2.44 KIPS |
|
Text Classification (HP)
|
71% |
3944
5.67 KIPS |
|
Text Classification (Q)
|
69% |
3896
5.71 KIPS |
|
Machine Translation (SP)
|
100% |
1926
33.2 IPS |
|
Machine Translation (HP)
|
100% |
2615
45.0 IPS |
|
Machine Translation (Q)
|
98% |
2589
44.7 IPS |