User | M91 |
Upload Date | April 06 2025 08:17 PM |
Views | 2 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A17 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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 | 7.50 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1703
316.7 IPS |
|
Image Classification (HP)
|
100% |
10990
2.04 KIPS |
|
Image Classification (Q)
|
97% |
15360
2.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1607
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
15794
256.0 IPS |
|
Image Segmentation (Q)
|
99% |
21277
344.9 IPS |
|
Pose Estimation (SP)
|
100% |
7842
9.15 IPS |
|
Pose Estimation (HP)
|
100% |
107028
124.9 IPS |
|
Pose Estimation (Q)
|
95% |
204724
239.9 IPS |
|
Object Detection (SP)
|
100% |
1787
141.7 IPS |
|
Object Detection (HP)
|
100% |
13881
1.10 KIPS |
|
Object Detection (Q)
|
91% |
19231
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3202
38.0 IPS |
|
Face Detection (HP)
|
100% |
36830
437.6 IPS |
|
Face Detection (Q)
|
100% |
51518
612.1 IPS |
|
Depth Estimation (SP)
|
100% |
6967
53.7 IPS |
|
Depth Estimation (HP)
|
99% |
78975
608.5 IPS |
|
Depth Estimation (Q)
|
85% |
126694
990.6 IPS |
|
Style Transfer (SP)
|
100% |
20953
26.9 IPS |
|
Style Transfer (HP)
|
100% |
205936
264.7 IPS |
|
Style Transfer (Q)
|
96% |
248995
321.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4818
177.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
34271
1.27 KIPS |
|
Image Super-Resolution (Q)
|
99% |
54892
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3244
4.33 KIPS |
|
Text Classification (HP)
|
100% |
2964
3.96 KIPS |
|
Text Classification (Q)
|
93% |
3271
4.39 KIPS |
|
Machine Translation (SP)
|
100% |
3226
55.6 IPS |
|
Machine Translation (HP)
|
100% |
6523
112.4 IPS |
|
Machine Translation (Q)
|
98% |
7866
135.9 IPS |