| User | M91 |
| Upload Date | August 22 2024 12:32 PM |
| Views | 7 |
| 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% |
300
55.8 IPS |
|
|
Image Classification (HP)
|
100% |
367
68.2 IPS |
|
|
Image Classification (Q)
|
99% |
372
69.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
311
5.03 IPS |
|
|
Image Segmentation (HP)
|
100% |
343
5.56 IPS |
|
|
Image Segmentation (Q)
|
100% |
349
5.65 IPS |
|
|
Pose Estimation (SP)
|
100% |
2369
2.76 IPS |
|
|
Pose Estimation (HP)
|
100% |
3161
3.69 IPS |
|
|
Pose Estimation (Q)
|
96% |
1183
1.39 IPS |
|
|
Object Detection (SP)
|
100% |
660
52.3 IPS |
|
|
Object Detection (HP)
|
100% |
625
49.6 IPS |
|
|
Object Detection (Q)
|
94% |
298
23.8 IPS |
|
|
Face Detection (SP)
|
100% |
2610
31.0 IPS |
|
|
Face Detection (HP)
|
100% |
3341
39.7 IPS |
|
|
Face Detection (Q)
|
100% |
371
4.40 IPS |
|
|
Depth Estimation (SP)
|
100% |
2522
19.4 IPS |
|
|
Depth Estimation (HP)
|
99% |
3576
27.6 IPS |
|
|
Depth Estimation (Q)
|
97% |
3544
27.4 IPS |
|
|
Style Transfer (SP)
|
100% |
6131
7.88 IPS |
|
|
Style Transfer (HP)
|
100% |
8562
11.0 IPS |
|
|
Style Transfer (Q)
|
100% |
8581
11.0 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1220
45.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1402
51.8 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
453
16.8 IPS |
|
|
Text Classification (SP)
|
100% |
233
311.0 IPS |
|
|
Text Classification (HP)
|
100% |
409
545.8 IPS |
|
|
Text Classification (Q)
|
93% |
404
541.6 IPS |
|
|
Machine Translation (SP)
|
100% |
260
4.48 IPS |
|
|
Machine Translation (HP)
|
100% |
238
4.09 IPS |
|
|
Machine Translation (Q)
|
98% |
233
4.03 IPS |