| User | mcx |
| Upload Date | August 15 2024 06:43 PM |
| Views | 9 |
| 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% |
470
87.3 IPS |
|
|
Image Classification (HP)
|
100% |
669
124.4 IPS |
|
|
Image Classification (Q)
|
99% |
665
124.1 IPS |
|
|
Image Segmentation (SP)
|
100% |
506
8.21 IPS |
|
|
Image Segmentation (HP)
|
100% |
605
9.80 IPS |
|
|
Image Segmentation (Q)
|
100% |
600
9.73 IPS |
|
|
Pose Estimation (SP)
|
100% |
2449
2.86 IPS |
|
|
Pose Estimation (HP)
|
100% |
2099
2.45 IPS |
|
|
Pose Estimation (Q)
|
96% |
1986
2.33 IPS |
|
|
Object Detection (SP)
|
100% |
498
39.5 IPS |
|
|
Object Detection (HP)
|
99% |
823
65.3 IPS |
|
|
Object Detection (Q)
|
92% |
659
52.6 IPS |
|
|
Face Detection (SP)
|
100% |
1096
13.0 IPS |
|
|
Face Detection (HP)
|
100% |
1873
22.3 IPS |
|
|
Face Detection (Q)
|
100% |
1266
15.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
1308
10.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
2004
15.5 IPS |
|
|
Depth Estimation (Q)
|
97% |
725
5.61 IPS |
|
|
Style Transfer (SP)
|
100% |
2733
3.51 IPS |
|
|
Style Transfer (HP)
|
100% |
3299
4.24 IPS |
|
|
Style Transfer (Q)
|
100% |
3318
4.26 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
905
33.4 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
373
13.8 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
887
32.9 IPS |
|
|
Text Classification (SP)
|
100% |
141
188.5 IPS |
|
|
Text Classification (HP)
|
99% |
323
431.5 IPS |
|
|
Text Classification (Q)
|
93% |
282
378.0 IPS |
|
|
Machine Translation (SP)
|
100% |
520
8.96 IPS |
|
|
Machine Translation (HP)
|
98% |
921
15.9 IPS |
|
|
Machine Translation (Q)
|
98% |
910
15.7 IPS |