User | Yearcakes |
Upload Date | June 21 2025 09:53 AM |
Views | 5 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A18 Pro |
System Information | |
---|---|
Operating System | iOS 18.5 |
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% |
2076
386.1 IPS |
|
Image Classification (HP)
|
100% |
15113
2.81 KIPS |
|
Image Classification (Q)
|
97% |
20427
3.81 KIPS |
|
Image Segmentation (SP)
|
100% |
2022
32.8 IPS |
|
Image Segmentation (HP)
|
100% |
18299
296.6 IPS |
|
Image Segmentation (Q)
|
99% |
24172
391.9 IPS |
|
Pose Estimation (SP)
|
100% |
10136
11.8 IPS |
|
Pose Estimation (HP)
|
100% |
153428
179.0 IPS |
|
Pose Estimation (Q)
|
95% |
292786
343.2 IPS |
|
Object Detection (SP)
|
100% |
2394
189.9 IPS |
|
Object Detection (HP)
|
100% |
15966
1.27 KIPS |
|
Object Detection (Q)
|
91% |
22647
1.81 KIPS |
|
Face Detection (SP)
|
100% |
4069
48.3 IPS |
|
Face Detection (HP)
|
100% |
41186
489.4 IPS |
|
Face Detection (Q)
|
100% |
58125
690.7 IPS |
|
Depth Estimation (SP)
|
100% |
8506
65.5 IPS |
|
Depth Estimation (HP)
|
99% |
95297
734.2 IPS |
|
Depth Estimation (Q)
|
85% |
161762
1.26 KIPS |
|
Style Transfer (SP)
|
100% |
22364
28.7 IPS |
|
Style Transfer (HP)
|
100% |
244958
314.9 IPS |
|
Style Transfer (Q)
|
96% |
300603
387.9 IPS |
|
Image Super-Resolution (SP)
|
100% |
5986
221.0 IPS |
|
Image Super-Resolution (HP)
|
100% |
50675
1.87 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84921
3.14 KIPS |
|
Text Classification (SP)
|
100% |
3377
4.51 KIPS |
|
Text Classification (HP)
|
100% |
4294
5.73 KIPS |
|
Text Classification (Q)
|
93% |
4956
6.65 KIPS |
|
Machine Translation (SP)
|
100% |
4222
72.7 IPS |
|
Machine Translation (HP)
|
100% |
9864
169.9 IPS |
|
Machine Translation (Q)
|
98% |
10956
189.3 IPS |