| User | M91 |
| Upload Date | August 24 2024 10:22 AM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| 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% |
295
54.9 IPS |
|
|
Image Classification (HP)
|
100% |
369
68.7 IPS |
|
|
Image Classification (Q)
|
99% |
359
66.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
313
5.08 IPS |
|
|
Image Segmentation (HP)
|
100% |
350
5.67 IPS |
|
|
Image Segmentation (Q)
|
100% |
348
5.64 IPS |
|
|
Pose Estimation (SP)
|
100% |
2370
2.77 IPS |
|
|
Pose Estimation (HP)
|
100% |
3206
3.74 IPS |
|
|
Pose Estimation (Q)
|
96% |
1202
1.41 IPS |
|
|
Object Detection (SP)
|
100% |
638
50.6 IPS |
|
|
Object Detection (HP)
|
100% |
714
56.7 IPS |
|
|
Object Detection (Q)
|
94% |
299
23.8 IPS |
|
|
Face Detection (SP)
|
100% |
2617
31.1 IPS |
|
|
Face Detection (HP)
|
100% |
3395
40.3 IPS |
|
|
Face Detection (Q)
|
100% |
379
4.50 IPS |
|
|
Depth Estimation (SP)
|
100% |
2505
19.3 IPS |
|
|
Depth Estimation (HP)
|
99% |
3507
27.0 IPS |
|
|
Depth Estimation (Q)
|
97% |
3497
27.0 IPS |
|
|
Style Transfer (SP)
|
100% |
6162
7.92 IPS |
|
|
Style Transfer (HP)
|
100% |
8584
11.0 IPS |
|
|
Style Transfer (Q)
|
100% |
8562
11.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1228
45.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1329
49.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
452
16.7 IPS |
|
|
Text Classification (SP)
|
100% |
232
310.1 IPS |
|
|
Text Classification (HP)
|
100% |
406
542.1 IPS |
|
|
Text Classification (Q)
|
93% |
405
543.2 IPS |
|
|
Machine Translation (SP)
|
100% |
262
4.51 IPS |
|
|
Machine Translation (HP)
|
100% |
233
4.01 IPS |
|
|
Machine Translation (Q)
|
98% |
236
4.08 IPS |