| Upload Date | December 17 2024 08:08 PM |
| Views | 19 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPhone 12 |
| Model ID | iPhone13,2 |
| Motherboard | D53gAP |
| 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 | 3.60 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1270
236.3 IPS |
|
|
Image Classification (HP)
|
100% |
1903
354.0 IPS |
|
|
Image Classification (Q)
|
96% |
1367
255.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1139
18.5 IPS |
|
|
Image Segmentation (HP)
|
100% |
1721
27.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
2134
34.6 IPS |
|
|
Pose Estimation (SP)
|
100% |
4827
5.63 IPS |
|
|
Pose Estimation (HP)
|
100% |
9586
11.2 IPS |
|
|
Pose Estimation (Q)
|
95% |
8599
10.1 IPS |
|
|
Object Detection (SP)
|
100% |
1247
98.9 IPS |
|
|
Object Detection (HP)
|
97% |
2067
164.6 IPS |
|
|
Object Detection (Q)
|
94% |
1457
116.1 IPS |
|
|
Face Detection (SP)
|
100% |
2405
28.6 IPS |
|
|
Face Detection (HP)
|
100% |
4546
54.0 IPS |
|
|
Face Detection (Q)
|
100% |
2538
30.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
4484
34.5 IPS |
|
|
Depth Estimation (HP)
|
98% |
8814
68.1 IPS |
|
|
Depth Estimation (Q)
|
85% |
6300
49.2 IPS |
|
|
Style Transfer (SP)
|
100% |
12043
15.5 IPS |
|
|
Style Transfer (HP)
|
100% |
20051
25.8 IPS |
|
|
Style Transfer (Q)
|
96% |
17387
22.4 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2594
95.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3773
139.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2907
107.3 IPS |
|
|
Text Classification (SP)
|
100% |
2091
2.79 KIPS |
|
|
Text Classification (HP)
|
100% |
3569
4.76 KIPS |
|
|
Text Classification (Q)
|
93% |
3558
4.78 KIPS |
|
|
Machine Translation (SP)
|
100% |
2247
38.7 IPS |
|
|
Machine Translation (HP)
|
98% |
3246
56.1 IPS |
|
|
Machine Translation (Q)
|
98% |
3697
63.9 IPS |