| User | alfred_heinze |
| Upload Date | March 22 2025 12:47 PM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.3.2 |
| Model | iPad mini (5th generation) |
| Model ID | iPad11,1 |
| Motherboard | J210AP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.85 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
374
69.5 IPS |
|
|
Image Classification (HP)
|
100% |
641
119.1 IPS |
|
|
Image Classification (Q)
|
96% |
530
99.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
410
6.65 IPS |
|
|
Image Segmentation (HP)
|
100% |
707
11.5 IPS |
|
|
Image Segmentation (Q)
|
99% |
764
12.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
1100
1.28 IPS |
|
|
Pose Estimation (HP)
|
100% |
1090
1.27 IPS |
|
|
Pose Estimation (Q)
|
96% |
1037
1.22 IPS |
|
|
Object Detection (SP)
|
100% |
341
27.0 IPS |
|
|
Object Detection (HP)
|
99% |
666
52.8 IPS |
|
|
Object Detection (Q)
|
92% |
545
43.5 IPS |
|
|
Face Detection (SP)
|
100% |
852
10.1 IPS |
|
|
Face Detection (HP)
|
100% |
1728
20.5 IPS |
|
|
Face Detection (Q)
|
100% |
1141
13.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
825
6.36 IPS |
|
|
Depth Estimation (HP)
|
98% |
1476
11.4 IPS |
|
|
Depth Estimation (Q)
|
85% |
1336
10.4 IPS |
|
|
Style Transfer (SP)
|
100% |
2093
2.69 IPS |
|
|
Style Transfer (HP)
|
100% |
3686
4.74 IPS |
|
|
Style Transfer (Q)
|
96% |
3587
4.63 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
621
22.9 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
822
30.3 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
709
26.2 IPS |
|
|
Text Classification (SP)
|
100% |
283
377.6 IPS |
|
|
Text Classification (HP)
|
100% |
560
748.1 IPS |
|
|
Text Classification (Q)
|
93% |
557
747.8 IPS |
|
|
Machine Translation (SP)
|
100% |
591
10.2 IPS |
|
|
Machine Translation (HP)
|
98% |
973
16.8 IPS |
|
|
Machine Translation (Q)
|
98% |
992
17.1 IPS |