| User | ju83 |
| Upload Date | September 10 2024 07:55 AM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPhone XS |
| Model ID | iPhone11,2 |
| Motherboard | D321AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
298
55.4 IPS |
|
|
Image Classification (HP)
|
100% |
502
93.4 IPS |
|
|
Image Classification (Q)
|
96% |
451
84.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
346
5.61 IPS |
|
|
Image Segmentation (HP)
|
100% |
455
7.38 IPS |
|
|
Image Segmentation (Q)
|
99% |
587
9.55 IPS |
|
|
Pose Estimation (SP)
|
100% |
959
1.12 IPS |
|
|
Pose Estimation (HP)
|
100% |
795
0.93 IPS |
|
|
Pose Estimation (Q)
|
96% |
820
0.96 IPS |
|
|
Object Detection (SP)
|
100% |
290
23.0 IPS |
|
|
Object Detection (HP)
|
99% |
607
48.2 IPS |
|
|
Object Detection (Q)
|
92% |
470
37.5 IPS |
|
|
Face Detection (SP)
|
100% |
738
8.76 IPS |
|
|
Face Detection (HP)
|
100% |
1440
17.1 IPS |
|
|
Face Detection (Q)
|
100% |
1007
12.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
649
5.00 IPS |
|
|
Depth Estimation (HP)
|
98% |
1340
10.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
1093
8.54 IPS |
|
|
Style Transfer (SP)
|
100% |
1711
2.20 IPS |
|
|
Style Transfer (HP)
|
100% |
3281
4.22 IPS |
|
|
Style Transfer (Q)
|
96% |
3144
4.06 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
523
19.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
812
30.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
684
25.3 IPS |
|
|
Text Classification (SP)
|
100% |
277
369.3 IPS |
|
|
Text Classification (HP)
|
100% |
553
738.7 IPS |
|
|
Text Classification (Q)
|
93% |
556
745.9 IPS |
|
|
Machine Translation (SP)
|
100% |
521
8.98 IPS |
|
|
Machine Translation (HP)
|
98% |
861
14.9 IPS |
|
|
Machine Translation (Q)
|
98% |
845
14.6 IPS |