Upload Date | September 18 2024 06:57 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.0 |
Model | iPhone 15 Plus |
Model ID | iPhone15,5 |
Motherboard | D38AP |
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 | 5.53 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1439
267.6 IPS |
|
Image Classification (HP)
|
100% |
9740
1.81 KIPS |
|
Image Classification (Q)
|
97% |
12376
2.31 KIPS |
|
Image Segmentation (SP)
|
100% |
1473
23.9 IPS |
|
Image Segmentation (HP)
|
100% |
11720
190.0 IPS |
|
Image Segmentation (Q)
|
99% |
13335
216.2 IPS |
|
Pose Estimation (SP)
|
100% |
6781
7.91 IPS |
|
Pose Estimation (HP)
|
100% |
96824
113.0 IPS |
|
Pose Estimation (Q)
|
95% |
101718
119.2 IPS |
|
Object Detection (SP)
|
100% |
1600
126.9 IPS |
|
Object Detection (HP)
|
100% |
12895
1.02 KIPS |
|
Object Detection (Q)
|
91% |
14867
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3338
39.7 IPS |
|
Face Detection (HP)
|
100% |
31117
369.7 IPS |
|
Face Detection (Q)
|
100% |
38595
458.6 IPS |
|
Depth Estimation (SP)
|
100% |
6181
47.6 IPS |
|
Depth Estimation (HP)
|
99% |
74436
573.5 IPS |
|
Depth Estimation (Q)
|
85% |
94681
740.3 IPS |
|
Style Transfer (SP)
|
100% |
18569
23.9 IPS |
|
Style Transfer (HP)
|
100% |
173602
223.2 IPS |
|
Style Transfer (Q)
|
96% |
173774
224.2 IPS |
|
Image Super-Resolution (SP)
|
100% |
4110
151.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
32519
1.20 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37177
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2609
3.48 KIPS |
|
Text Classification (HP)
|
100% |
2005
2.68 KIPS |
|
Text Classification (Q)
|
93% |
2281
3.06 KIPS |
|
Machine Translation (SP)
|
100% |
3440
59.3 IPS |
|
Machine Translation (HP)
|
100% |
2226
38.3 IPS |
|
Machine Translation (Q)
|
98% |
2268
39.2 IPS |