User | M91 |
Upload Date | August 24 2024 10:31 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% |
1669
310.3 IPS |
|
Image Classification (HP)
|
100% |
10730
2.00 KIPS |
|
Image Classification (Q)
|
99% |
12899
2.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1584
25.7 IPS |
|
Image Segmentation (HP)
|
100% |
10597
171.8 IPS |
|
Image Segmentation (Q)
|
100% |
10567
171.3 IPS |
|
Pose Estimation (SP)
|
100% |
7484
8.73 IPS |
|
Pose Estimation (HP)
|
100% |
102870
120.0 IPS |
|
Pose Estimation (Q)
|
94% |
197080
231.2 IPS |
|
Object Detection (SP)
|
100% |
1778
141.1 IPS |
|
Object Detection (HP)
|
100% |
12847
1.02 KIPS |
|
Object Detection (Q)
|
91% |
18045
1.44 KIPS |
|
Face Detection (SP)
|
100% |
3190
37.9 IPS |
|
Face Detection (HP)
|
100% |
21701
257.9 IPS |
|
Face Detection (Q)
|
100% |
35177
418.0 IPS |
|
Depth Estimation (SP)
|
100% |
7010
54.0 IPS |
|
Depth Estimation (HP)
|
99% |
65004
500.8 IPS |
|
Depth Estimation (Q)
|
97% |
74141
573.3 IPS |
|
Style Transfer (SP)
|
100% |
20565
26.4 IPS |
|
Style Transfer (HP)
|
100% |
138131
177.6 IPS |
|
Style Transfer (Q)
|
100% |
139502
179.3 IPS |
|
Image Super-Resolution (SP)
|
100% |
4766
176.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
34565
1.28 KIPS |
|
Image Super-Resolution (Q)
|
98% |
54443
2.02 KIPS |
|
Text Classification (SP)
|
100% |
3104
4.14 KIPS |
|
Text Classification (HP)
|
100% |
2587
3.45 KIPS |
|
Text Classification (Q)
|
93% |
1754
2.35 KIPS |
|
Machine Translation (SP)
|
100% |
3125
53.8 IPS |
|
Machine Translation (HP)
|
100% |
6320
108.9 IPS |
|
Machine Translation (Q)
|
98% |
7345
126.9 IPS |