| Upload Date | October 07 2024 07:22 PM |
| Views | 1 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0.1 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
269
50.1 IPS |
|
|
Image Classification (HP)
|
100% |
1964
365.3 IPS |
|
|
Image Classification (Q)
|
99% |
172
32.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
256
4.15 IPS |
|
|
Image Segmentation (HP)
|
100% |
386
6.25 IPS |
|
|
Image Segmentation (Q)
|
99% |
202
3.27 IPS |
|
|
Pose Estimation (SP)
|
100% |
1125
1.31 IPS |
|
|
Pose Estimation (HP)
|
100% |
24381
28.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
843
0.99 IPS |
|
|
Object Detection (SP)
|
100% |
270
21.4 IPS |
|
|
Object Detection (HP)
|
100% |
1401
111.1 IPS |
|
|
Object Detection (Q)
|
94% |
200
15.9 IPS |
|
|
Face Detection (SP)
|
100% |
643
7.64 IPS |
|
|
Face Detection (HP)
|
100% |
5227
62.1 IPS |
|
|
Face Detection (Q)
|
100% |
260
3.08 IPS |
|
|
Depth Estimation (SP)
|
100% |
665
5.12 IPS |
|
|
Depth Estimation (HP)
|
99% |
18414
141.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
452
3.53 IPS |
|
|
Style Transfer (SP)
|
100% |
1786
2.30 IPS |
|
|
Style Transfer (HP)
|
100% |
1771
2.28 IPS |
|
|
Style Transfer (Q)
|
96% |
1457
1.88 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
559
20.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3520
130.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
489
18.0 IPS |
|
|
Text Classification (SP)
|
100% |
268
358.1 IPS |
|
|
Text Classification (HP)
|
100% |
305
407.1 IPS |
|
|
Text Classification (Q)
|
93% |
299
401.4 IPS |
|
|
Machine Translation (SP)
|
100% |
426
7.34 IPS |
|
|
Machine Translation (HP)
|
100% |
327
5.63 IPS |
|
|
Machine Translation (Q)
|
98% |
323
5.58 IPS |