Upload Date | January 07 2025 03:29 AM |
Views | 1 |
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% |
1661
308.9 IPS |
|
Image Classification (HP)
|
100% |
10650
1.98 KIPS |
|
Image Classification (Q)
|
97% |
15545
2.90 KIPS |
|
Image Segmentation (SP)
|
100% |
1598
25.9 IPS |
|
Image Segmentation (HP)
|
100% |
15628
253.3 IPS |
|
Image Segmentation (Q)
|
99% |
20779
336.8 IPS |
|
Pose Estimation (SP)
|
100% |
7540
8.80 IPS |
|
Pose Estimation (HP)
|
100% |
106265
124.0 IPS |
|
Pose Estimation (Q)
|
95% |
203289
238.3 IPS |
|
Object Detection (SP)
|
100% |
1757
139.3 IPS |
|
Object Detection (HP)
|
100% |
13720
1.09 KIPS |
|
Object Detection (Q)
|
91% |
19047
1.52 KIPS |
|
Face Detection (SP)
|
100% |
3145
37.4 IPS |
|
Face Detection (HP)
|
100% |
35512
422.0 IPS |
|
Face Detection (Q)
|
100% |
51199
608.4 IPS |
|
Depth Estimation (SP)
|
100% |
6859
52.8 IPS |
|
Depth Estimation (HP)
|
99% |
77898
600.2 IPS |
|
Depth Estimation (Q)
|
85% |
127363
995.8 IPS |
|
Style Transfer (SP)
|
100% |
20146
25.9 IPS |
|
Style Transfer (HP)
|
100% |
203748
261.9 IPS |
|
Style Transfer (Q)
|
96% |
251566
324.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
4682
172.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34230
1.26 KIPS |
|
Image Super-Resolution (Q)
|
99% |
57262
2.11 KIPS |
|
Text Classification (SP)
|
100% |
3197
4.27 KIPS |
|
Text Classification (HP)
|
100% |
3115
4.16 KIPS |
|
Text Classification (Q)
|
93% |
3269
4.39 KIPS |
|
Machine Translation (SP)
|
100% |
3098
53.4 IPS |
|
Machine Translation (HP)
|
100% |
6678
115.0 IPS |
|
Machine Translation (Q)
|
98% |
7362
127.2 IPS |