| User | M91 |
| Upload Date | November 23 2024 01:28 PM |
| Views | 7 |
| 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% |
299
55.6 IPS |
|
|
Image Classification (HP)
|
100% |
355
66.0 IPS |
|
|
Image Classification (Q)
|
97% |
241
45.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
316
5.12 IPS |
|
|
Image Segmentation (HP)
|
100% |
341
5.53 IPS |
|
|
Image Segmentation (Q)
|
99% |
343
5.56 IPS |
|
|
Pose Estimation (SP)
|
100% |
2363
2.76 IPS |
|
|
Pose Estimation (HP)
|
100% |
3161
3.69 IPS |
|
|
Pose Estimation (Q)
|
95% |
1264
1.48 IPS |
|
|
Object Detection (SP)
|
100% |
666
52.8 IPS |
|
|
Object Detection (HP)
|
100% |
658
52.2 IPS |
|
|
Object Detection (Q)
|
94% |
298
23.7 IPS |
|
|
Face Detection (SP)
|
100% |
2604
30.9 IPS |
|
|
Face Detection (HP)
|
100% |
3345
39.7 IPS |
|
|
Face Detection (Q)
|
100% |
372
4.42 IPS |
|
|
Depth Estimation (SP)
|
100% |
2493
19.2 IPS |
|
|
Depth Estimation (HP)
|
99% |
3460
26.7 IPS |
|
|
Depth Estimation (Q)
|
86% |
1022
7.98 IPS |
|
|
Style Transfer (SP)
|
100% |
6135
7.89 IPS |
|
|
Style Transfer (HP)
|
100% |
8627
11.1 IPS |
|
|
Style Transfer (Q)
|
96% |
2102
2.71 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1211
44.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1252
46.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
456
16.8 IPS |
|
|
Text Classification (SP)
|
100% |
233
310.7 IPS |
|
|
Text Classification (HP)
|
100% |
406
542.0 IPS |
|
|
Text Classification (Q)
|
93% |
406
545.4 IPS |
|
|
Machine Translation (SP)
|
100% |
259
4.47 IPS |
|
|
Machine Translation (HP)
|
100% |
225
3.88 IPS |
|
|
Machine Translation (Q)
|
98% |
224
3.87 IPS |