User | 2048 |
Upload Date | August 21 2024 04:46 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% |
1670
310.6 IPS |
|
Image Classification (HP)
|
100% |
11494
2.14 KIPS |
|
Image Classification (Q)
|
99% |
13172
2.46 KIPS |
|
Image Segmentation (SP)
|
100% |
1688
27.4 IPS |
|
Image Segmentation (HP)
|
100% |
10506
170.3 IPS |
|
Image Segmentation (Q)
|
100% |
10648
172.6 IPS |
|
Pose Estimation (SP)
|
100% |
7454
8.70 IPS |
|
Pose Estimation (HP)
|
100% |
100554
117.3 IPS |
|
Pose Estimation (Q)
|
94% |
199263
233.7 IPS |
|
Object Detection (SP)
|
100% |
1699
134.8 IPS |
|
Object Detection (HP)
|
100% |
13071
1.04 KIPS |
|
Object Detection (Q)
|
91% |
19181
1.53 KIPS |
|
Face Detection (SP)
|
100% |
3131
37.2 IPS |
|
Face Detection (HP)
|
100% |
21646
257.2 IPS |
|
Face Detection (Q)
|
100% |
36948
439.0 IPS |
|
Depth Estimation (SP)
|
100% |
6878
53.0 IPS |
|
Depth Estimation (HP)
|
99% |
64889
499.9 IPS |
|
Depth Estimation (Q)
|
97% |
74179
573.6 IPS |
|
Style Transfer (SP)
|
100% |
20067
25.8 IPS |
|
Style Transfer (HP)
|
100% |
139610
179.5 IPS |
|
Style Transfer (Q)
|
100% |
140552
180.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
4505
166.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
34033
1.26 KIPS |
|
Image Super-Resolution (Q)
|
98% |
57309
2.12 KIPS |
|
Text Classification (SP)
|
100% |
3164
4.22 KIPS |
|
Text Classification (HP)
|
100% |
2291
3.06 KIPS |
|
Text Classification (Q)
|
93% |
2365
3.17 KIPS |
|
Machine Translation (SP)
|
100% |
3146
54.2 IPS |
|
Machine Translation (HP)
|
100% |
6083
104.8 IPS |
|
Machine Translation (Q)
|
98% |
7902
136.6 IPS |