| User | M91 |
| Upload Date | November 19 2024 01:53 PM |
| Views | 8 |
| 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% |
307
57.1 IPS |
|
|
Image Classification (HP)
|
100% |
366
68.1 IPS |
|
|
Image Classification (Q)
|
97% |
242
45.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
316
5.13 IPS |
|
|
Image Segmentation (HP)
|
100% |
349
5.65 IPS |
|
|
Image Segmentation (Q)
|
99% |
344
5.57 IPS |
|
|
Pose Estimation (SP)
|
100% |
2371
2.77 IPS |
|
|
Pose Estimation (HP)
|
100% |
3195
3.73 IPS |
|
|
Pose Estimation (Q)
|
95% |
1245
1.46 IPS |
|
|
Object Detection (SP)
|
100% |
641
50.9 IPS |
|
|
Object Detection (HP)
|
100% |
657
52.1 IPS |
|
|
Object Detection (Q)
|
94% |
299
23.8 IPS |
|
|
Face Detection (SP)
|
100% |
2605
31.0 IPS |
|
|
Face Detection (HP)
|
100% |
3354
39.9 IPS |
|
|
Face Detection (Q)
|
100% |
381
4.53 IPS |
|
|
Depth Estimation (SP)
|
100% |
2524
19.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
3500
27.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
1029
8.03 IPS |
|
|
Style Transfer (SP)
|
100% |
6158
7.92 IPS |
|
|
Style Transfer (HP)
|
100% |
8616
11.1 IPS |
|
|
Style Transfer (Q)
|
96% |
2085
2.69 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1219
45.0 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1332
49.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
461
17.0 IPS |
|
|
Text Classification (SP)
|
100% |
234
312.5 IPS |
|
|
Text Classification (HP)
|
100% |
410
547.9 IPS |
|
|
Text Classification (Q)
|
93% |
406
544.3 IPS |
|
|
Machine Translation (SP)
|
100% |
264
4.55 IPS |
|
|
Machine Translation (HP)
|
100% |
233
4.02 IPS |
|
|
Machine Translation (Q)
|
98% |
221
3.82 IPS |