| User | M91 |
| Upload Date | November 18 2024 12:21 PM |
| Views | 10 |
| 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% |
290
54.0 IPS |
|
|
Image Classification (HP)
|
100% |
367
68.3 IPS |
|
|
Image Classification (Q)
|
97% |
242
45.2 IPS |
|
|
Image Segmentation (SP)
|
100% |
311
5.04 IPS |
|
|
Image Segmentation (HP)
|
100% |
356
5.78 IPS |
|
|
Image Segmentation (Q)
|
99% |
344
5.58 IPS |
|
|
Pose Estimation (SP)
|
100% |
2370
2.76 IPS |
|
|
Pose Estimation (HP)
|
100% |
3205
3.74 IPS |
|
|
Pose Estimation (Q)
|
95% |
1241
1.45 IPS |
|
|
Object Detection (SP)
|
100% |
686
54.4 IPS |
|
|
Object Detection (HP)
|
100% |
691
54.8 IPS |
|
|
Object Detection (Q)
|
94% |
299
23.8 IPS |
|
|
Face Detection (SP)
|
100% |
2597
30.9 IPS |
|
|
Face Detection (HP)
|
100% |
3368
40.0 IPS |
|
|
Face Detection (Q)
|
100% |
334
3.97 IPS |
|
|
Depth Estimation (SP)
|
100% |
2525
19.5 IPS |
|
|
Depth Estimation (HP)
|
99% |
3519
27.1 IPS |
|
|
Depth Estimation (Q)
|
86% |
996
7.78 IPS |
|
|
Style Transfer (SP)
|
100% |
6142
7.90 IPS |
|
|
Style Transfer (HP)
|
100% |
8602
11.1 IPS |
|
|
Style Transfer (Q)
|
96% |
2092
2.70 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1230
45.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1321
48.8 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
461
17.0 IPS |
|
|
Text Classification (SP)
|
100% |
231
307.9 IPS |
|
|
Text Classification (HP)
|
100% |
408
544.8 IPS |
|
|
Text Classification (Q)
|
93% |
404
542.3 IPS |
|
|
Machine Translation (SP)
|
100% |
267
4.61 IPS |
|
|
Machine Translation (HP)
|
100% |
238
4.10 IPS |
|
|
Machine Translation (Q)
|
98% |
225
3.89 IPS |