Upload Date | November 20 2024 10:28 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
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% |
1702
316.5 IPS |
|
Image Classification (HP)
|
100% |
10882
2.02 KIPS |
|
Image Classification (Q)
|
97% |
15109
2.82 KIPS |
|
Image Segmentation (SP)
|
100% |
1613
26.2 IPS |
|
Image Segmentation (HP)
|
100% |
15756
255.4 IPS |
|
Image Segmentation (Q)
|
99% |
21428
347.4 IPS |
|
Pose Estimation (SP)
|
100% |
7601
8.87 IPS |
|
Pose Estimation (HP)
|
100% |
105123
122.7 IPS |
|
Pose Estimation (Q)
|
95% |
204990
240.3 IPS |
|
Object Detection (SP)
|
100% |
1773
140.7 IPS |
|
Object Detection (HP)
|
100% |
14059
1.12 KIPS |
|
Object Detection (Q)
|
91% |
19379
1.55 KIPS |
|
Face Detection (SP)
|
100% |
3217
38.2 IPS |
|
Face Detection (HP)
|
100% |
35003
415.9 IPS |
|
Face Detection (Q)
|
100% |
52192
620.2 IPS |
|
Depth Estimation (SP)
|
100% |
6964
53.7 IPS |
|
Depth Estimation (HP)
|
99% |
78708
606.4 IPS |
|
Depth Estimation (Q)
|
85% |
132599
1.04 KIPS |
|
Style Transfer (SP)
|
100% |
20118
25.9 IPS |
|
Style Transfer (HP)
|
100% |
204222
262.5 IPS |
|
Style Transfer (Q)
|
96% |
250331
323.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4811
177.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
34357
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
59748
2.21 KIPS |
|
Text Classification (SP)
|
100% |
3183
4.25 KIPS |
|
Text Classification (HP)
|
100% |
3476
4.64 KIPS |
|
Text Classification (Q)
|
93% |
3148
4.22 KIPS |
|
Machine Translation (SP)
|
100% |
3115
53.7 IPS |
|
Machine Translation (HP)
|
100% |
6274
108.1 IPS |
|
Machine Translation (Q)
|
98% |
7791
134.6 IPS |