Upload Date | January 04 2025 03:29 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.2 |
Model | iPhone 15 |
Model ID | iPhone15,4 |
Motherboard | D37AP |
CPU Information | |
---|---|
Name | Apple A16 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.46 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.56 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1434
266.8 IPS |
|
Image Classification (HP)
|
100% |
10423
1.94 KIPS |
|
Image Classification (Q)
|
97% |
12141
2.27 KIPS |
|
Image Segmentation (SP)
|
100% |
1463
23.7 IPS |
|
Image Segmentation (HP)
|
100% |
14671
237.8 IPS |
|
Image Segmentation (Q)
|
99% |
18105
293.5 IPS |
|
Pose Estimation (SP)
|
100% |
6769
7.90 IPS |
|
Pose Estimation (HP)
|
100% |
98039
114.4 IPS |
|
Pose Estimation (Q)
|
95% |
101041
118.4 IPS |
|
Object Detection (SP)
|
100% |
1592
126.2 IPS |
|
Object Detection (HP)
|
100% |
12850
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14818
1.18 KIPS |
|
Face Detection (SP)
|
100% |
3087
36.7 IPS |
|
Face Detection (HP)
|
100% |
31084
369.3 IPS |
|
Face Detection (Q)
|
100% |
39862
473.6 IPS |
|
Depth Estimation (SP)
|
100% |
6137
47.3 IPS |
|
Depth Estimation (HP)
|
99% |
74375
573.0 IPS |
|
Depth Estimation (Q)
|
85% |
96573
755.1 IPS |
|
Style Transfer (SP)
|
100% |
18930
24.3 IPS |
|
Style Transfer (HP)
|
100% |
172140
221.3 IPS |
|
Style Transfer (Q)
|
96% |
173547
224.0 IPS |
|
Image Super-Resolution (SP)
|
100% |
4237
156.5 IPS |
|
Image Super-Resolution (HP)
|
100% |
33428
1.23 KIPS |
|
Image Super-Resolution (Q)
|
99% |
39785
1.47 KIPS |
|
Text Classification (SP)
|
100% |
2643
3.53 KIPS |
|
Text Classification (HP)
|
100% |
2088
2.79 KIPS |
|
Text Classification (Q)
|
93% |
1543
2.07 KIPS |
|
Machine Translation (SP)
|
100% |
3480
59.9 IPS |
|
Machine Translation (HP)
|
100% |
7311
125.9 IPS |
|
Machine Translation (Q)
|
98% |
8094
139.9 IPS |