User | Meandro |
Upload Date | April 04 2025 02:06 PM |
Views | 7 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.4 |
Model | iPhone 16 Pro |
Model ID | iPhone17,1 |
Motherboard | D93AP |
CPU Information | |
---|---|
Name | Apple A18 Pro |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 4.04 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 7.47 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
2067
384.4 IPS |
|
Image Classification (HP)
|
100% |
15222
2.83 KIPS |
|
Image Classification (Q)
|
97% |
20870
3.89 KIPS |
|
Image Segmentation (SP)
|
100% |
2013
32.6 IPS |
|
Image Segmentation (HP)
|
100% |
18313
296.9 IPS |
|
Image Segmentation (Q)
|
99% |
24129
391.2 IPS |
|
Pose Estimation (SP)
|
100% |
9110
10.6 IPS |
|
Pose Estimation (HP)
|
100% |
152350
177.8 IPS |
|
Pose Estimation (Q)
|
95% |
291637
341.8 IPS |
|
Object Detection (SP)
|
100% |
2356
186.9 IPS |
|
Object Detection (HP)
|
100% |
16134
1.28 KIPS |
|
Object Detection (Q)
|
91% |
22856
1.83 KIPS |
|
Face Detection (SP)
|
100% |
3975
47.2 IPS |
|
Face Detection (HP)
|
100% |
40195
477.6 IPS |
|
Face Detection (Q)
|
100% |
57751
686.2 IPS |
|
Depth Estimation (SP)
|
100% |
8293
63.9 IPS |
|
Depth Estimation (HP)
|
99% |
94814
730.5 IPS |
|
Depth Estimation (Q)
|
85% |
161795
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
20750
26.7 IPS |
|
Style Transfer (HP)
|
100% |
244726
314.6 IPS |
|
Style Transfer (Q)
|
96% |
298682
385.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
5691
210.1 IPS |
|
Image Super-Resolution (HP)
|
100% |
50721
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
85589
3.16 KIPS |
|
Text Classification (SP)
|
100% |
3408
4.55 KIPS |
|
Text Classification (HP)
|
100% |
2724
3.64 KIPS |
|
Text Classification (Q)
|
93% |
4092
5.49 KIPS |
|
Machine Translation (SP)
|
100% |
4282
73.8 IPS |
|
Machine Translation (HP)
|
100% |
9916
170.8 IPS |
|
Machine Translation (Q)
|
98% |
10789
186.5 IPS |