Upload Date | September 05 2025 01:02 PM |
Views | 3 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.6.2 |
Model | iPhone 13 Pro |
Model ID | iPhone14,2 |
Motherboard | D63AP |
CPU Information | |
---|---|
Name | Apple A15 Bionic |
Topology | 1 Processor, 6 Cores |
Identifier | ARM |
Base Frequency | 3.23 GHz |
Cluster 1 | 2 Cores |
Cluster 2 | 4 Cores |
Memory Information | |
---|---|
Size | 5.54 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1339
249.0 IPS |
|
Image Classification (HP)
|
100% |
8065
1.50 KIPS |
|
Image Classification (Q)
|
96% |
10673
1.99 KIPS |
|
Image Segmentation (SP)
|
100% |
1267
20.5 IPS |
|
Image Segmentation (HP)
|
100% |
13210
214.1 IPS |
|
Image Segmentation (Q)
|
99% |
15053
244.0 IPS |
|
Pose Estimation (SP)
|
100% |
5916
6.90 IPS |
|
Pose Estimation (HP)
|
100% |
91114
106.3 IPS |
|
Pose Estimation (Q)
|
95% |
93130
109.2 IPS |
|
Object Detection (SP)
|
100% |
1393
110.5 IPS |
|
Object Detection (HP)
|
99% |
11314
900.0 IPS |
|
Object Detection (Q)
|
91% |
11881
949.4 IPS |
|
Face Detection (SP)
|
100% |
2576
30.6 IPS |
|
Face Detection (HP)
|
100% |
28453
338.1 IPS |
|
Face Detection (Q)
|
100% |
36154
429.6 IPS |
|
Depth Estimation (SP)
|
100% |
5115
39.4 IPS |
|
Depth Estimation (HP)
|
99% |
53539
412.5 IPS |
|
Depth Estimation (Q)
|
85% |
81141
634.1 IPS |
|
Style Transfer (SP)
|
100% |
16369
21.0 IPS |
|
Style Transfer (HP)
|
100% |
157649
202.7 IPS |
|
Style Transfer (Q)
|
96% |
164724
212.6 IPS |
|
Image Super-Resolution (SP)
|
100% |
3708
136.9 IPS |
|
Image Super-Resolution (HP)
|
100% |
27403
1.01 KIPS |
|
Image Super-Resolution (Q)
|
99% |
30319
1.12 KIPS |
|
Text Classification (SP)
|
100% |
2461
3.28 KIPS |
|
Text Classification (HP)
|
100% |
2514
3.36 KIPS |
|
Text Classification (Q)
|
93% |
2543
3.41 KIPS |
|
Machine Translation (SP)
|
100% |
3526
60.7 IPS |
|
Machine Translation (HP)
|
100% |
6421
110.6 IPS |
|
Machine Translation (Q)
|
98% |
7196
124.4 IPS |