Upload Date | November 09 2024 03:34 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 | 5.55 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1419
263.9 IPS |
|
Image Classification (HP)
|
100% |
9938
1.85 KIPS |
|
Image Classification (Q)
|
97% |
12906
2.41 KIPS |
|
Image Segmentation (SP)
|
100% |
1468
23.8 IPS |
|
Image Segmentation (HP)
|
100% |
14288
231.6 IPS |
|
Image Segmentation (Q)
|
99% |
18139
294.0 IPS |
|
Pose Estimation (SP)
|
100% |
6332
7.39 IPS |
|
Pose Estimation (HP)
|
100% |
97567
113.8 IPS |
|
Pose Estimation (Q)
|
95% |
102062
119.6 IPS |
|
Object Detection (SP)
|
100% |
1550
122.9 IPS |
|
Object Detection (HP)
|
100% |
13029
1.03 KIPS |
|
Object Detection (Q)
|
91% |
14903
1.19 KIPS |
|
Face Detection (SP)
|
100% |
3161
37.6 IPS |
|
Face Detection (HP)
|
100% |
31446
373.7 IPS |
|
Face Detection (Q)
|
100% |
41032
487.6 IPS |
|
Depth Estimation (SP)
|
100% |
5814
44.8 IPS |
|
Depth Estimation (HP)
|
99% |
74761
576.0 IPS |
|
Depth Estimation (Q)
|
85% |
94699
740.4 IPS |
|
Style Transfer (SP)
|
100% |
17098
22.0 IPS |
|
Style Transfer (HP)
|
100% |
173240
222.7 IPS |
|
Style Transfer (Q)
|
96% |
174172
224.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
3888
143.6 IPS |
|
Image Super-Resolution (HP)
|
100% |
30948
1.14 KIPS |
|
Image Super-Resolution (Q)
|
99% |
37066
1.37 KIPS |
|
Text Classification (SP)
|
100% |
2618
3.49 KIPS |
|
Text Classification (HP)
|
100% |
1929
2.57 KIPS |
|
Text Classification (Q)
|
93% |
1918
2.57 KIPS |
|
Machine Translation (SP)
|
100% |
3392
58.4 IPS |
|
Machine Translation (HP)
|
100% |
7236
124.7 IPS |
|
Machine Translation (Q)
|
98% |
7961
137.6 IPS |