User | M91 |
Upload Date | October 17 2024 11:07 PM |
Views | 5 |
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% |
1726
321.0 IPS |
|
Image Classification (HP)
|
100% |
11057
2.06 KIPS |
|
Image Classification (Q)
|
97% |
15020
2.80 KIPS |
|
Image Segmentation (SP)
|
100% |
1625
26.3 IPS |
|
Image Segmentation (HP)
|
100% |
16053
260.2 IPS |
|
Image Segmentation (Q)
|
99% |
20933
339.3 IPS |
|
Pose Estimation (SP)
|
100% |
8065
9.41 IPS |
|
Pose Estimation (HP)
|
100% |
106559
124.3 IPS |
|
Pose Estimation (Q)
|
95% |
203828
238.9 IPS |
|
Object Detection (SP)
|
100% |
1821
144.5 IPS |
|
Object Detection (HP)
|
100% |
13941
1.11 KIPS |
|
Object Detection (Q)
|
91% |
19254
1.54 KIPS |
|
Face Detection (SP)
|
100% |
3284
39.0 IPS |
|
Face Detection (HP)
|
100% |
34498
409.9 IPS |
|
Face Detection (Q)
|
100% |
50087
595.1 IPS |
|
Depth Estimation (SP)
|
100% |
7219
55.6 IPS |
|
Depth Estimation (HP)
|
99% |
78955
608.3 IPS |
|
Depth Estimation (Q)
|
85% |
129933
1.02 KIPS |
|
Style Transfer (SP)
|
100% |
21368
27.5 IPS |
|
Style Transfer (HP)
|
100% |
203071
261.1 IPS |
|
Style Transfer (Q)
|
96% |
247623
319.5 IPS |
|
Image Super-Resolution (SP)
|
100% |
4988
184.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
35056
1.29 KIPS |
|
Image Super-Resolution (Q)
|
99% |
55527
2.05 KIPS |
|
Text Classification (SP)
|
100% |
3205
4.28 KIPS |
|
Text Classification (HP)
|
100% |
2939
3.92 KIPS |
|
Text Classification (Q)
|
93% |
3228
4.33 KIPS |
|
Machine Translation (SP)
|
100% |
3141
54.1 IPS |
|
Machine Translation (HP)
|
100% |
6287
108.3 IPS |
|
Machine Translation (Q)
|
98% |
7298
126.1 IPS |