User | kochitora |
Upload Date | January 02 2025 12:07 AM |
Views | 4 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 |
System Information | |
---|---|
Operating System | iOS 18.1.1 |
Model | iPhone 16 |
Model ID | iPhone17,3 |
Motherboard | D47AP |
CPU Information | |
---|---|
Name | Apple A18 |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.52 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1921
357.3 IPS |
|
Image Classification (HP)
|
100% |
15412
2.87 KIPS |
|
Image Classification (Q)
|
97% |
21275
3.97 KIPS |
|
Image Segmentation (SP)
|
100% |
1786
29.0 IPS |
|
Image Segmentation (HP)
|
100% |
18169
294.5 IPS |
|
Image Segmentation (Q)
|
99% |
23728
384.7 IPS |
|
Pose Estimation (SP)
|
100% |
8797
10.3 IPS |
|
Pose Estimation (HP)
|
100% |
155206
181.1 IPS |
|
Pose Estimation (Q)
|
95% |
295751
346.6 IPS |
|
Object Detection (SP)
|
100% |
2115
167.7 IPS |
|
Object Detection (HP)
|
100% |
16604
1.32 KIPS |
|
Object Detection (Q)
|
91% |
22696
1.81 KIPS |
|
Face Detection (SP)
|
100% |
3330
39.6 IPS |
|
Face Detection (HP)
|
100% |
42429
504.1 IPS |
|
Face Detection (Q)
|
100% |
55298
657.1 IPS |
|
Depth Estimation (SP)
|
100% |
7650
58.9 IPS |
|
Depth Estimation (HP)
|
99% |
95846
738.4 IPS |
|
Depth Estimation (Q)
|
85% |
162774
1.27 KIPS |
|
Style Transfer (SP)
|
100% |
23062
29.6 IPS |
|
Style Transfer (HP)
|
100% |
244547
314.4 IPS |
|
Style Transfer (Q)
|
96% |
304381
392.8 IPS |
|
Image Super-Resolution (SP)
|
100% |
5444
201.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
50075
1.85 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84864
3.13 KIPS |
|
Text Classification (SP)
|
100% |
3435
4.59 KIPS |
|
Text Classification (HP)
|
100% |
4859
6.49 KIPS |
|
Text Classification (Q)
|
93% |
4867
6.53 KIPS |
|
Machine Translation (SP)
|
100% |
3605
62.1 IPS |
|
Machine Translation (HP)
|
100% |
9896
170.5 IPS |
|
Machine Translation (Q)
|
98% |
11796
203.9 IPS |