User | Ricochet |
Upload Date | September 02 2024 06:29 AM |
Views | 3 |
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% |
1458
271.1 IPS |
|
Image Classification (HP)
|
100% |
6288
1.17 KIPS |
|
Image Classification (Q)
|
99% |
6913
1.29 KIPS |
|
Image Segmentation (SP)
|
100% |
821
13.3 IPS |
|
Image Segmentation (HP)
|
100% |
5224
84.7 IPS |
|
Image Segmentation (Q)
|
100% |
5200
84.3 IPS |
|
Pose Estimation (SP)
|
100% |
7998
9.33 IPS |
|
Pose Estimation (HP)
|
100% |
87766
102.4 IPS |
|
Pose Estimation (Q)
|
94% |
111508
130.8 IPS |
|
Object Detection (SP)
|
100% |
1335
105.9 IPS |
|
Object Detection (HP)
|
100% |
7446
590.7 IPS |
|
Object Detection (Q)
|
93% |
8012
639.3 IPS |
|
Face Detection (SP)
|
100% |
1629
19.4 IPS |
|
Face Detection (HP)
|
100% |
6903
82.0 IPS |
|
Face Detection (Q)
|
100% |
11683
138.8 IPS |
|
Depth Estimation (SP)
|
100% |
3588
27.6 IPS |
|
Depth Estimation (HP)
|
99% |
41718
321.4 IPS |
|
Depth Estimation (Q)
|
97% |
44854
346.8 IPS |
|
Style Transfer (SP)
|
100% |
11647
15.0 IPS |
|
Style Transfer (HP)
|
100% |
128662
165.4 IPS |
|
Style Transfer (Q)
|
100% |
128273
164.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
3725
137.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
18399
679.4 IPS |
|
Image Super-Resolution (Q)
|
98% |
26818
993.6 IPS |
|
Text Classification (SP)
|
100% |
1733
2.31 KIPS |
|
Text Classification (HP)
|
71% |
5136
7.38 KIPS |
|
Text Classification (Q)
|
69% |
5044
7.39 KIPS |
|
Machine Translation (SP)
|
100% |
1887
32.5 IPS |
|
Machine Translation (HP)
|
100% |
2415
41.6 IPS |
|
Machine Translation (Q)
|
98% |
2460
42.5 IPS |