| User | jobieh |
| Upload Date | May 31 2025 06:18 AM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.5 |
| Model | iPad (8th generation) |
| Model ID | iPad11,6 |
| Motherboard | J171aAP |
| 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 | 2.88 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
231
42.9 IPS |
|
|
Image Classification (HP)
|
100% |
443
82.3 IPS |
|
|
Image Classification (Q)
|
96% |
399
74.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
270
4.38 IPS |
|
|
Image Segmentation (HP)
|
100% |
427
6.92 IPS |
|
|
Image Segmentation (Q)
|
99% |
578
9.40 IPS |
|
|
Pose Estimation (SP)
|
100% |
673
0.79 IPS |
|
|
Pose Estimation (HP)
|
100% |
784
0.91 IPS |
|
|
Pose Estimation (Q)
|
96% |
852
1.00 IPS |
|
|
Object Detection (SP)
|
100% |
285
22.6 IPS |
|
|
Object Detection (HP)
|
99% |
619
49.1 IPS |
|
|
Object Detection (Q)
|
92% |
525
41.9 IPS |
|
|
Face Detection (SP)
|
100% |
864
10.3 IPS |
|
|
Face Detection (HP)
|
100% |
1666
19.8 IPS |
|
|
Face Detection (Q)
|
100% |
1068
12.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
747
5.76 IPS |
|
|
Depth Estimation (HP)
|
98% |
1348
10.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
1246
9.73 IPS |
|
|
Style Transfer (SP)
|
100% |
1840
2.37 IPS |
|
|
Style Transfer (HP)
|
100% |
3403
4.37 IPS |
|
|
Style Transfer (Q)
|
96% |
2974
3.84 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
580
21.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
774
28.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
686
25.3 IPS |
|
|
Text Classification (SP)
|
100% |
241
321.2 IPS |
|
|
Text Classification (HP)
|
100% |
556
742.0 IPS |
|
|
Text Classification (Q)
|
93% |
555
745.5 IPS |
|
|
Machine Translation (SP)
|
100% |
494
8.51 IPS |
|
|
Machine Translation (HP)
|
98% |
995
17.2 IPS |
|
|
Machine Translation (Q)
|
98% |
944
16.3 IPS |