User | cuber |
Upload Date | September 08 2024 07:19 PM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 17.6.1 |
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% |
1460
271.6 IPS |
|
Image Classification (HP)
|
100% |
6228
1.16 KIPS |
|
Image Classification (Q)
|
97% |
7853
1.47 KIPS |
|
Image Segmentation (SP)
|
100% |
813
13.2 IPS |
|
Image Segmentation (HP)
|
100% |
5231
84.8 IPS |
|
Image Segmentation (Q)
|
99% |
10037
162.7 IPS |
|
Pose Estimation (SP)
|
100% |
7576
8.84 IPS |
|
Pose Estimation (HP)
|
100% |
88593
103.4 IPS |
|
Pose Estimation (Q)
|
95% |
153406
179.8 IPS |
|
Object Detection (SP)
|
100% |
1501
119.0 IPS |
|
Object Detection (HP)
|
100% |
8180
648.9 IPS |
|
Object Detection (Q)
|
93% |
9998
797.7 IPS |
|
Face Detection (SP)
|
100% |
2337
27.8 IPS |
|
Face Detection (HP)
|
100% |
11205
133.1 IPS |
|
Face Detection (Q)
|
100% |
13225
157.1 IPS |
|
Depth Estimation (SP)
|
100% |
4865
37.5 IPS |
|
Depth Estimation (HP)
|
99% |
43778
337.3 IPS |
|
Depth Estimation (Q)
|
85% |
62873
491.6 IPS |
|
Style Transfer (SP)
|
100% |
12689
16.3 IPS |
|
Style Transfer (HP)
|
100% |
128777
165.5 IPS |
|
Style Transfer (Q)
|
96% |
137876
177.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
4288
158.3 IPS |
|
Image Super-Resolution (HP)
|
100% |
18493
682.9 IPS |
|
Image Super-Resolution (Q)
|
99% |
26121
964.5 IPS |
|
Text Classification (SP)
|
100% |
1834
2.45 KIPS |
|
Text Classification (HP)
|
71% |
3935
5.66 KIPS |
|
Text Classification (Q)
|
69% |
3965
5.81 KIPS |
|
Machine Translation (SP)
|
100% |
1940
33.4 IPS |
|
Machine Translation (HP)
|
100% |
2637
45.4 IPS |
|
Machine Translation (Q)
|
98% |
2618
45.2 IPS |