| User | Stephen_L |
| Upload Date | August 26 2024 09:07 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 12 Pro |
| Model ID | iPhone13,3 |
| Motherboard | D53pAP |
| CPU Information | |
|---|---|
| Name | Apple A14 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.99 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.54 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
497
92.5 IPS |
|
|
Image Classification (HP)
|
100% |
874
162.4 IPS |
|
|
Image Classification (Q)
|
99% |
826
154.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
560
9.08 IPS |
|
|
Image Segmentation (HP)
|
100% |
3268
53.0 IPS |
|
|
Image Segmentation (Q)
|
100% |
3875
62.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4103
4.79 IPS |
|
|
Pose Estimation (HP)
|
100% |
62043
72.4 IPS |
|
|
Pose Estimation (Q)
|
95% |
3619
4.24 IPS |
|
|
Object Detection (SP)
|
100% |
951
75.4 IPS |
|
|
Object Detection (HP)
|
98% |
936
74.5 IPS |
|
|
Object Detection (Q)
|
93% |
5540
442.0 IPS |
|
|
Face Detection (SP)
|
100% |
1622
19.3 IPS |
|
|
Face Detection (HP)
|
100% |
11165
132.7 IPS |
|
|
Face Detection (Q)
|
100% |
494
5.87 IPS |
|
|
Depth Estimation (SP)
|
100% |
2819
21.7 IPS |
|
|
Depth Estimation (HP)
|
98% |
3398
26.3 IPS |
|
|
Depth Estimation (Q)
|
96% |
3105
24.0 IPS |
|
|
Style Transfer (SP)
|
100% |
7820
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
10335
13.3 IPS |
|
|
Style Transfer (Q)
|
100% |
10161
13.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2227
82.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2409
88.9 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
868
32.2 IPS |
|
|
Text Classification (SP)
|
100% |
1150
1.54 KIPS |
|
|
Text Classification (HP)
|
100% |
529
705.4 IPS |
|
|
Text Classification (Q)
|
93% |
751
1.01 KIPS |
|
|
Machine Translation (SP)
|
100% |
1299
22.4 IPS |
|
|
Machine Translation (HP)
|
96% |
1625
28.1 IPS |
|
|
Machine Translation (Q)
|
98% |
1517
26.2 IPS |