Upload Date | September 17 2024 07:10 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% |
1443
268.4 IPS |
|
Image Classification (HP)
|
100% |
10284
1.91 KIPS |
|
Image Classification (Q)
|
97% |
13046
2.43 KIPS |
|
Image Segmentation (SP)
|
100% |
1469
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
11613
188.2 IPS |
|
Image Segmentation (Q)
|
99% |
13799
223.7 IPS |
|
Pose Estimation (SP)
|
100% |
7009
8.18 IPS |
|
Pose Estimation (HP)
|
100% |
96574
112.7 IPS |
|
Pose Estimation (Q)
|
95% |
102882
120.6 IPS |
|
Object Detection (SP)
|
100% |
1599
126.8 IPS |
|
Object Detection (HP)
|
100% |
12926
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14595
1.17 KIPS |
|
Face Detection (SP)
|
100% |
3243
38.5 IPS |
|
Face Detection (HP)
|
100% |
31035
368.8 IPS |
|
Face Detection (Q)
|
100% |
38794
461.0 IPS |
|
Depth Estimation (SP)
|
100% |
6220
47.9 IPS |
|
Depth Estimation (HP)
|
99% |
75390
580.8 IPS |
|
Depth Estimation (Q)
|
85% |
94581
739.5 IPS |
|
Style Transfer (SP)
|
100% |
18862
24.2 IPS |
|
Style Transfer (HP)
|
100% |
173607
223.2 IPS |
|
Style Transfer (Q)
|
96% |
173905
224.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
4190
154.7 IPS |
|
Image Super-Resolution (HP)
|
100% |
31642
1.17 KIPS |
|
Image Super-Resolution (Q)
|
99% |
36802
1.36 KIPS |
|
Text Classification (SP)
|
100% |
2624
3.50 KIPS |
|
Text Classification (HP)
|
100% |
2199
2.94 KIPS |
|
Text Classification (Q)
|
93% |
2340
3.14 KIPS |
|
Machine Translation (SP)
|
100% |
3420
58.9 IPS |
|
Machine Translation (HP)
|
100% |
2399
41.3 IPS |
|
Machine Translation (Q)
|
98% |
2388
41.3 IPS |