| User | Strumbull |
| Upload Date | August 24 2024 07:08 PM |
| Views | 20 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,1 |
| Motherboard | J317AP |
| CPU Information | |
|---|---|
| Name | Apple A12X Bionic |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 4 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
185
34.3 IPS |
|
|
Image Classification (HP)
|
100% |
309
57.4 IPS |
|
|
Image Classification (Q)
|
99% |
309
57.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
248
4.02 IPS |
|
|
Image Segmentation (HP)
|
100% |
578
9.37 IPS |
|
|
Image Segmentation (Q)
|
100% |
478
7.74 IPS |
|
|
Pose Estimation (SP)
|
100% |
1747
2.04 IPS |
|
|
Pose Estimation (HP)
|
100% |
1708
1.99 IPS |
|
|
Pose Estimation (Q)
|
96% |
1582
1.85 IPS |
|
|
Object Detection (SP)
|
100% |
488
38.7 IPS |
|
|
Object Detection (HP)
|
99% |
594
47.1 IPS |
|
|
Object Detection (Q)
|
92% |
605
48.2 IPS |
|
|
Face Detection (SP)
|
100% |
553
6.57 IPS |
|
|
Face Detection (HP)
|
100% |
1615
19.2 IPS |
|
|
Face Detection (Q)
|
100% |
1115
13.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
910
7.01 IPS |
|
|
Depth Estimation (HP)
|
99% |
2202
17.0 IPS |
|
|
Depth Estimation (Q)
|
97% |
885
6.84 IPS |
|
|
Style Transfer (SP)
|
100% |
3271
4.21 IPS |
|
|
Style Transfer (HP)
|
100% |
6502
8.36 IPS |
|
|
Style Transfer (Q)
|
100% |
6537
8.40 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
884
32.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1411
52.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
1169
43.3 IPS |
|
|
Text Classification (SP)
|
100% |
289
385.5 IPS |
|
|
Text Classification (HP)
|
99% |
554
740.1 IPS |
|
|
Text Classification (Q)
|
93% |
555
745.1 IPS |
|
|
Machine Translation (SP)
|
100% |
686
11.8 IPS |
|
|
Machine Translation (HP)
|
98% |
1079
18.7 IPS |
|
|
Machine Translation (Q)
|
98% |
1091
18.9 IPS |