| User | hermeschen1116 |
| Upload Date | December 30 2024 11:45 AM |
| Views | 9 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A14 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.3 |
| 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% |
1199
222.9 IPS |
|
|
Image Classification (HP)
|
100% |
1895
352.4 IPS |
|
|
Image Classification (Q)
|
96% |
1345
251.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
1057
17.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
1597
25.9 IPS |
|
|
Image Segmentation (Q)
|
99% |
1962
31.8 IPS |
|
|
Pose Estimation (SP)
|
100% |
4081
4.76 IPS |
|
|
Pose Estimation (HP)
|
100% |
8277
9.66 IPS |
|
|
Pose Estimation (Q)
|
95% |
7414
8.69 IPS |
|
|
Object Detection (SP)
|
100% |
1125
89.3 IPS |
|
|
Object Detection (HP)
|
97% |
1952
155.4 IPS |
|
|
Object Detection (Q)
|
94% |
1382
110.1 IPS |
|
|
Face Detection (SP)
|
100% |
2300
27.3 IPS |
|
|
Face Detection (HP)
|
100% |
4188
49.8 IPS |
|
|
Face Detection (Q)
|
100% |
2144
25.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
3918
30.2 IPS |
|
|
Depth Estimation (HP)
|
98% |
8261
63.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
5496
43.0 IPS |
|
|
Style Transfer (SP)
|
100% |
10315
13.3 IPS |
|
|
Style Transfer (HP)
|
100% |
17884
23.0 IPS |
|
|
Style Transfer (Q)
|
96% |
15379
19.8 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
2220
82.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3534
130.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
2436
89.9 IPS |
|
|
Text Classification (SP)
|
100% |
1951
2.60 KIPS |
|
|
Text Classification (HP)
|
100% |
3472
4.63 KIPS |
|
|
Text Classification (Q)
|
93% |
3499
4.70 KIPS |
|
|
Machine Translation (SP)
|
100% |
2017
34.7 IPS |
|
|
Machine Translation (HP)
|
98% |
3010
52.0 IPS |
|
|
Machine Translation (Q)
|
98% |
3128
54.1 IPS |