User | M91 |
Upload Date | September 05 2024 11:44 AM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1 |
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 | 7.51 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1725
320.8 IPS |
|
Image Classification (HP)
|
100% |
10778
2.00 KIPS |
|
Image Classification (Q)
|
99% |
13076
2.44 KIPS |
|
Image Segmentation (SP)
|
100% |
1630
26.4 IPS |
|
Image Segmentation (HP)
|
100% |
10832
175.6 IPS |
|
Image Segmentation (Q)
|
100% |
10643
172.5 IPS |
|
Pose Estimation (SP)
|
100% |
8044
9.39 IPS |
|
Pose Estimation (HP)
|
100% |
102776
119.9 IPS |
|
Pose Estimation (Q)
|
94% |
197725
231.9 IPS |
|
Object Detection (SP)
|
100% |
1811
143.7 IPS |
|
Object Detection (HP)
|
100% |
13129
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18598
1.49 KIPS |
|
Face Detection (SP)
|
100% |
3267
38.8 IPS |
|
Face Detection (HP)
|
100% |
21794
259.0 IPS |
|
Face Detection (Q)
|
100% |
35127
417.4 IPS |
|
Depth Estimation (SP)
|
100% |
7213
55.6 IPS |
|
Depth Estimation (HP)
|
99% |
64952
500.4 IPS |
|
Depth Estimation (Q)
|
97% |
74266
574.2 IPS |
|
Style Transfer (SP)
|
100% |
20971
27.0 IPS |
|
Style Transfer (HP)
|
100% |
139461
179.3 IPS |
|
Style Transfer (Q)
|
100% |
140419
180.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4899
180.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34433
1.27 KIPS |
|
Image Super-Resolution (Q)
|
98% |
54964
2.04 KIPS |
|
Text Classification (SP)
|
100% |
3204
4.28 KIPS |
|
Text Classification (HP)
|
100% |
2754
3.68 KIPS |
|
Text Classification (Q)
|
93% |
1881
2.52 KIPS |
|
Machine Translation (SP)
|
100% |
3142
54.1 IPS |
|
Machine Translation (HP)
|
100% |
6146
105.9 IPS |
|
Machine Translation (Q)
|
98% |
7324
126.6 IPS |