User | DAnaselo |
Upload Date | July 10 2025 01:27 PM |
Views | 8 |
AI Information | |
---|---|
Framework | Core ML |
Backend | Neural Engine |
Device | Apple A15 Bionic |
System Information | |
---|---|
Operating System | iOS 18.5 |
Model | iPhone 13 |
Model ID | iPhone14,5 |
Motherboard | D17AP |
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 | 3.58 GB |
Workload | Accuracy | Score | |
---|---|---|---|
Image Classification (SP)
|
100% |
1312
244.0 IPS |
|
Image Classification (HP)
|
100% |
8747
1.63 KIPS |
|
Image Classification (Q)
|
96% |
10024
1.87 KIPS |
|
Image Segmentation (SP)
|
100% |
1284
20.8 IPS |
|
Image Segmentation (HP)
|
100% |
13173
213.5 IPS |
|
Image Segmentation (Q)
|
99% |
14953
242.4 IPS |
|
Pose Estimation (SP)
|
100% |
5659
6.60 IPS |
|
Pose Estimation (HP)
|
100% |
89918
104.9 IPS |
|
Pose Estimation (Q)
|
95% |
94264
110.5 IPS |
|
Object Detection (SP)
|
100% |
1339
106.2 IPS |
|
Object Detection (HP)
|
99% |
10655
847.6 IPS |
|
Object Detection (Q)
|
91% |
11941
954.1 IPS |
|
Face Detection (SP)
|
100% |
2637
31.3 IPS |
|
Face Detection (HP)
|
100% |
27902
331.5 IPS |
|
Face Detection (Q)
|
100% |
35935
427.0 IPS |
|
Depth Estimation (SP)
|
100% |
5082
39.2 IPS |
|
Depth Estimation (HP)
|
99% |
56509
435.4 IPS |
|
Depth Estimation (Q)
|
85% |
81739
638.8 IPS |
|
Style Transfer (SP)
|
100% |
16113
20.7 IPS |
|
Style Transfer (HP)
|
100% |
160129
205.8 IPS |
|
Style Transfer (Q)
|
96% |
171567
221.4 IPS |
|
Image Super-Resolution (SP)
|
100% |
3634
134.2 IPS |
|
Image Super-Resolution (HP)
|
100% |
27497
1.02 KIPS |
|
Image Super-Resolution (Q)
|
99% |
30957
1.14 KIPS |
|
Text Classification (SP)
|
100% |
2451
3.27 KIPS |
|
Text Classification (HP)
|
100% |
2530
3.38 KIPS |
|
Text Classification (Q)
|
93% |
2573
3.45 KIPS |
|
Machine Translation (SP)
|
100% |
3610
62.2 IPS |
|
Machine Translation (HP)
|
100% |
6633
114.3 IPS |
|
Machine Translation (Q)
|
98% |
7263
125.5 IPS |