| Upload Date | August 16 2024 12:39 PM |
| Views | 86 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone 11 |
| Model ID | iPhone12,1 |
| Motherboard | N104AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.76 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
738
137.3 IPS |
|
|
Image Classification (HP)
|
100% |
1144
212.8 IPS |
|
|
Image Classification (Q)
|
99% |
1143
213.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
684
11.1 IPS |
|
|
Image Segmentation (HP)
|
100% |
768
12.4 IPS |
|
|
Image Segmentation (Q)
|
100% |
763
12.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
3237
3.78 IPS |
|
|
Pose Estimation (HP)
|
100% |
5860
6.84 IPS |
|
|
Pose Estimation (Q)
|
96% |
5314
6.23 IPS |
|
|
Object Detection (SP)
|
100% |
670
53.2 IPS |
|
|
Object Detection (HP)
|
97% |
1267
100.8 IPS |
|
|
Object Detection (Q)
|
94% |
970
77.3 IPS |
|
|
Face Detection (SP)
|
100% |
1330
15.8 IPS |
|
|
Face Detection (HP)
|
100% |
2575
30.6 IPS |
|
|
Face Detection (Q)
|
100% |
1550
18.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
2612
20.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
4632
35.8 IPS |
|
|
Depth Estimation (Q)
|
96% |
2041
15.8 IPS |
|
|
Style Transfer (SP)
|
100% |
5430
6.98 IPS |
|
|
Style Transfer (HP)
|
100% |
12246
15.7 IPS |
|
|
Style Transfer (Q)
|
100% |
12243
15.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1904
70.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2621
96.8 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
2042
75.6 IPS |
|
|
Text Classification (SP)
|
100% |
1415
1.89 KIPS |
|
|
Text Classification (HP)
|
100% |
2391
3.19 KIPS |
|
|
Text Classification (Q)
|
93% |
2391
3.21 KIPS |
|
|
Machine Translation (SP)
|
100% |
963
16.6 IPS |
|
|
Machine Translation (HP)
|
98% |
2301
39.8 IPS |
|
|
Machine Translation (Q)
|
98% |
2314
40.0 IPS |