User | Vinpeom |
Upload Date | May 14 2025 12:57 PM |
Views | 4 |
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% |
2082
387.2 IPS |
|
Image Classification (HP)
|
100% |
15259
2.84 KIPS |
|
Image Classification (Q)
|
97% |
21066
3.93 KIPS |
|
Image Segmentation (SP)
|
100% |
2006
32.5 IPS |
|
Image Segmentation (HP)
|
100% |
18345
297.4 IPS |
|
Image Segmentation (Q)
|
99% |
24138
391.3 IPS |
|
Pose Estimation (SP)
|
100% |
9271
10.8 IPS |
|
Pose Estimation (HP)
|
100% |
153742
179.4 IPS |
|
Pose Estimation (Q)
|
95% |
292475
342.8 IPS |
|
Object Detection (SP)
|
100% |
2350
186.4 IPS |
|
Object Detection (HP)
|
100% |
16332
1.30 KIPS |
|
Object Detection (Q)
|
91% |
22810
1.82 KIPS |
|
Face Detection (SP)
|
100% |
4022
47.8 IPS |
|
Face Detection (HP)
|
100% |
40255
478.3 IPS |
|
Face Detection (Q)
|
100% |
57871
687.6 IPS |
|
Depth Estimation (SP)
|
100% |
8342
64.3 IPS |
|
Depth Estimation (HP)
|
99% |
95294
734.2 IPS |
|
Depth Estimation (Q)
|
85% |
159385
1.25 KIPS |
|
Style Transfer (SP)
|
100% |
20901
26.9 IPS |
|
Style Transfer (HP)
|
100% |
244687
314.5 IPS |
|
Style Transfer (Q)
|
96% |
302794
390.7 IPS |
|
Image Super-Resolution (SP)
|
100% |
5670
209.4 IPS |
|
Image Super-Resolution (HP)
|
100% |
50832
1.88 KIPS |
|
Image Super-Resolution (Q)
|
99% |
84368
3.12 KIPS |
|
Text Classification (SP)
|
100% |
3373
4.50 KIPS |
|
Text Classification (HP)
|
100% |
4390
5.86 KIPS |
|
Text Classification (Q)
|
93% |
4441
5.96 KIPS |
|
Machine Translation (SP)
|
100% |
4305
74.2 IPS |
|
Machine Translation (HP)
|
100% |
10273
177.0 IPS |
|
Machine Translation (Q)
|
98% |
11421
197.4 IPS |