| User | M91 |
| Upload Date | December 11 2024 11:05 AM |
| Views | 5 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| Model | iPad (9th generation) |
| Model ID | iPad12,1 |
| Motherboard | J181AP |
| 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 | 2.87 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
298
55.5 IPS |
|
|
Image Classification (HP)
|
100% |
362
67.3 IPS |
|
|
Image Classification (Q)
|
97% |
242
45.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
312
5.05 IPS |
|
|
Image Segmentation (HP)
|
100% |
337
5.46 IPS |
|
|
Image Segmentation (Q)
|
99% |
341
5.53 IPS |
|
|
Pose Estimation (SP)
|
100% |
2350
2.74 IPS |
|
|
Pose Estimation (HP)
|
100% |
3130
3.65 IPS |
|
|
Pose Estimation (Q)
|
95% |
1225
1.44 IPS |
|
|
Object Detection (SP)
|
100% |
674
53.5 IPS |
|
|
Object Detection (HP)
|
100% |
665
52.7 IPS |
|
|
Object Detection (Q)
|
94% |
299
23.8 IPS |
|
|
Face Detection (SP)
|
100% |
2514
29.9 IPS |
|
|
Face Detection (HP)
|
100% |
3380
40.2 IPS |
|
|
Face Detection (Q)
|
100% |
378
4.49 IPS |
|
|
Depth Estimation (SP)
|
100% |
2521
19.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
3526
27.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
1007
7.86 IPS |
|
|
Style Transfer (SP)
|
100% |
6134
7.89 IPS |
|
|
Style Transfer (HP)
|
100% |
8586
11.0 IPS |
|
|
Style Transfer (Q)
|
96% |
2067
2.67 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1223
45.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1328
49.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
461
17.0 IPS |
|
|
Text Classification (SP)
|
100% |
232
309.2 IPS |
|
|
Text Classification (HP)
|
100% |
407
543.8 IPS |
|
|
Text Classification (Q)
|
93% |
406
545.0 IPS |
|
|
Machine Translation (SP)
|
100% |
264
4.54 IPS |
|
|
Machine Translation (HP)
|
100% |
236
4.06 IPS |
|
|
Machine Translation (Q)
|
98% |
226
3.90 IPS |