| User | M91 |
| Upload Date | September 24 2024 11:36 AM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| 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% |
291
54.1 IPS |
|
|
Image Classification (HP)
|
100% |
359
66.8 IPS |
|
|
Image Classification (Q)
|
97% |
240
44.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
309
5.00 IPS |
|
|
Image Segmentation (HP)
|
100% |
342
5.54 IPS |
|
|
Image Segmentation (Q)
|
99% |
332
5.38 IPS |
|
|
Pose Estimation (SP)
|
100% |
2350
2.74 IPS |
|
|
Pose Estimation (HP)
|
100% |
3202
3.74 IPS |
|
|
Pose Estimation (Q)
|
95% |
1321
1.55 IPS |
|
|
Object Detection (SP)
|
100% |
662
52.5 IPS |
|
|
Object Detection (HP)
|
100% |
638
50.6 IPS |
|
|
Object Detection (Q)
|
94% |
293
23.4 IPS |
|
|
Face Detection (SP)
|
100% |
2590
30.8 IPS |
|
|
Face Detection (HP)
|
100% |
3355
39.9 IPS |
|
|
Face Detection (Q)
|
100% |
363
4.31 IPS |
|
|
Depth Estimation (SP)
|
100% |
2505
19.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
3621
27.9 IPS |
|
|
Depth Estimation (Q)
|
86% |
989
7.72 IPS |
|
|
Style Transfer (SP)
|
100% |
6111
7.86 IPS |
|
|
Style Transfer (HP)
|
100% |
8550
11.0 IPS |
|
|
Style Transfer (Q)
|
96% |
2072
2.67 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1220
45.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1425
52.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
457
16.9 IPS |
|
|
Text Classification (SP)
|
100% |
234
312.1 IPS |
|
|
Text Classification (HP)
|
100% |
373
498.2 IPS |
|
|
Text Classification (Q)
|
93% |
370
496.8 IPS |
|
|
Machine Translation (SP)
|
100% |
262
4.51 IPS |
|
|
Machine Translation (HP)
|
100% |
212
3.65 IPS |
|
|
Machine Translation (Q)
|
98% |
205
3.55 IPS |