Upload Date | September 18 2024 07:02 PM |
Views | 1 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A16 Bionic |
System Information | |
---|---|
Operating System | iOS 18.1 |
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% |
1436
267.1 IPS |
|
Image Classification (HP)
|
100% |
10177
1.89 KIPS |
|
Image Classification (Q)
|
97% |
12795
2.39 KIPS |
|
Image Segmentation (SP)
|
100% |
1478
24.0 IPS |
|
Image Segmentation (HP)
|
100% |
12104
196.2 IPS |
|
Image Segmentation (Q)
|
99% |
13414
217.4 IPS |
|
Pose Estimation (SP)
|
100% |
6060
7.07 IPS |
|
Pose Estimation (HP)
|
100% |
98663
115.1 IPS |
|
Pose Estimation (Q)
|
95% |
102945
120.7 IPS |
|
Object Detection (SP)
|
100% |
1545
122.6 IPS |
|
Object Detection (HP)
|
100% |
12907
1.02 KIPS |
|
Object Detection (Q)
|
91% |
15025
1.20 KIPS |
|
Face Detection (SP)
|
100% |
3258
38.7 IPS |
|
Face Detection (HP)
|
100% |
30830
366.3 IPS |
|
Face Detection (Q)
|
100% |
37592
446.7 IPS |
|
Depth Estimation (SP)
|
100% |
5882
45.3 IPS |
|
Depth Estimation (HP)
|
99% |
74499
574.0 IPS |
|
Depth Estimation (Q)
|
85% |
94335
737.6 IPS |
|
Style Transfer (SP)
|
100% |
17093
22.0 IPS |
|
Style Transfer (HP)
|
100% |
174607
224.5 IPS |
|
Style Transfer (Q)
|
96% |
173425
223.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3867
142.8 IPS |
|
Image Super-Resolution (HP)
|
100% |
32177
1.19 KIPS |
|
Image Super-Resolution (Q)
|
99% |
38430
1.42 KIPS |
|
Text Classification (SP)
|
100% |
2631
3.51 KIPS |
|
Text Classification (HP)
|
100% |
1675
2.24 KIPS |
|
Text Classification (Q)
|
93% |
1591
2.14 KIPS |
|
Machine Translation (SP)
|
100% |
3363
57.9 IPS |
|
Machine Translation (HP)
|
100% |
2244
38.7 IPS |
|
Machine Translation (Q)
|
98% |
2194
37.9 IPS |