User | M91 |
Upload Date | August 29 2024 11:45 AM |
Views | 2 |
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% |
1657
308.2 IPS |
|
Image Classification (HP)
|
100% |
10510
1.95 KIPS |
|
Image Classification (Q)
|
99% |
12726
2.37 KIPS |
|
Image Segmentation (SP)
|
100% |
1606
26.0 IPS |
|
Image Segmentation (HP)
|
100% |
10733
174.0 IPS |
|
Image Segmentation (Q)
|
100% |
10690
173.3 IPS |
|
Pose Estimation (SP)
|
100% |
7295
8.51 IPS |
|
Pose Estimation (HP)
|
100% |
100381
117.1 IPS |
|
Pose Estimation (Q)
|
94% |
198031
232.3 IPS |
|
Object Detection (SP)
|
100% |
1766
140.0 IPS |
|
Object Detection (HP)
|
100% |
13048
1.04 KIPS |
|
Object Detection (Q)
|
91% |
18310
1.46 KIPS |
|
Face Detection (SP)
|
100% |
3170
37.7 IPS |
|
Face Detection (HP)
|
100% |
21992
261.3 IPS |
|
Face Detection (Q)
|
100% |
35416
420.8 IPS |
|
Depth Estimation (SP)
|
100% |
6945
53.5 IPS |
|
Depth Estimation (HP)
|
99% |
64207
494.7 IPS |
|
Depth Estimation (Q)
|
97% |
73788
570.5 IPS |
|
Style Transfer (SP)
|
100% |
20238
26.0 IPS |
|
Style Transfer (HP)
|
100% |
138613
178.2 IPS |
|
Style Transfer (Q)
|
100% |
139261
179.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4768
176.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
34501
1.27 KIPS |
|
Image Super-Resolution (Q)
|
98% |
54782
2.03 KIPS |
|
Text Classification (SP)
|
100% |
3174
4.24 KIPS |
|
Text Classification (HP)
|
100% |
3068
4.10 KIPS |
|
Text Classification (Q)
|
93% |
3142
4.22 KIPS |
|
Machine Translation (SP)
|
100% |
3161
54.4 IPS |
|
Machine Translation (HP)
|
100% |
6091
104.9 IPS |
|
Machine Translation (Q)
|
98% |
7289
126.0 IPS |