| User | ju83 |
| Upload Date | November 28 2024 07:55 AM |
| Views | 16 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1.1 |
| 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% |
333
62.0 IPS |
|
|
Image Classification (HP)
|
100% |
594
110.4 IPS |
|
|
Image Classification (Q)
|
96% |
499
93.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
342
5.55 IPS |
|
|
Image Segmentation (HP)
|
100% |
607
9.83 IPS |
|
|
Image Segmentation (Q)
|
99% |
690
11.2 IPS |
|
|
Pose Estimation (SP)
|
100% |
895
1.04 IPS |
|
|
Pose Estimation (HP)
|
100% |
732
0.85 IPS |
|
|
Pose Estimation (Q)
|
96% |
728
0.85 IPS |
|
|
Object Detection (SP)
|
100% |
282
22.3 IPS |
|
|
Object Detection (HP)
|
99% |
587
46.6 IPS |
|
|
Object Detection (Q)
|
92% |
514
41.0 IPS |
|
|
Face Detection (SP)
|
100% |
735
8.73 IPS |
|
|
Face Detection (HP)
|
100% |
1208
14.4 IPS |
|
|
Face Detection (Q)
|
100% |
1042
12.4 IPS |
|
|
Depth Estimation (SP)
|
100% |
617
4.76 IPS |
|
|
Depth Estimation (HP)
|
98% |
1085
8.39 IPS |
|
|
Depth Estimation (Q)
|
85% |
988
7.72 IPS |
|
|
Style Transfer (SP)
|
100% |
1518
1.95 IPS |
|
|
Style Transfer (HP)
|
100% |
2689
3.46 IPS |
|
|
Style Transfer (Q)
|
96% |
2647
3.42 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
511
18.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
582
21.5 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
604
22.3 IPS |
|
|
Text Classification (SP)
|
100% |
251
335.6 IPS |
|
|
Text Classification (HP)
|
100% |
477
636.4 IPS |
|
|
Text Classification (Q)
|
93% |
495
664.6 IPS |
|
|
Machine Translation (SP)
|
100% |
513
8.84 IPS |
|
|
Machine Translation (HP)
|
98% |
948
16.4 IPS |
|
|
Machine Translation (Q)
|
98% |
944
16.3 IPS |