| Upload Date | October 11 2024 02:15 PM |
| Views | 17 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPhone 14 Pro |
| Model ID | iPhone15,2 |
| Motherboard | D73AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.53 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1434
266.7 IPS |
|
|
Image Classification (HP)
|
100% |
9610
1.79 KIPS |
|
|
Image Classification (Q)
|
97% |
11436
2.13 KIPS |
|
|
Image Segmentation (SP)
|
100% |
1444
23.4 IPS |
|
|
Image Segmentation (HP)
|
100% |
14582
236.4 IPS |
|
|
Image Segmentation (Q)
|
99% |
17987
291.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
7165
8.36 IPS |
|
|
Pose Estimation (HP)
|
100% |
97006
113.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
101352
118.8 IPS |
|
|
Object Detection (SP)
|
100% |
1588
126.0 IPS |
|
|
Object Detection (HP)
|
100% |
12478
989.7 IPS |
|
|
Object Detection (Q)
|
91% |
14115
1.13 KIPS |
|
|
Face Detection (SP)
|
100% |
3137
37.3 IPS |
|
|
Face Detection (HP)
|
100% |
30052
357.1 IPS |
|
|
Face Detection (Q)
|
100% |
38842
461.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
6248
48.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
74566
574.5 IPS |
|
|
Depth Estimation (Q)
|
85% |
95149
743.9 IPS |
|
|
Style Transfer (SP)
|
100% |
18974
24.4 IPS |
|
|
Style Transfer (HP)
|
100% |
168636
216.8 IPS |
|
|
Style Transfer (Q)
|
96% |
169566
218.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
4236
156.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
32484
1.20 KIPS |
|
|
Image Super-Resolution (Q)
|
99% |
35621
1.32 KIPS |
|
|
Text Classification (SP)
|
100% |
2555
3.41 KIPS |
|
|
Text Classification (HP)
|
100% |
2017
2.69 KIPS |
|
|
Text Classification (Q)
|
93% |
2160
2.90 KIPS |
|
|
Machine Translation (SP)
|
100% |
3390
58.4 IPS |
|
|
Machine Translation (HP)
|
100% |
5533
95.3 IPS |
|
|
Machine Translation (Q)
|
98% |
6089
105.2 IPS |