| User | anbG34 |
| Upload Date | May 19 2025 11:34 AM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.5 |
| Model | iPad Pro (11-inch) |
| Model ID | iPad8,3 |
| Motherboard | J318AP |
| 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 | 3.70 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
477
88.7 IPS |
|
|
Image Classification (HP)
|
100% |
782
145.5 IPS |
|
|
Image Classification (Q)
|
96% |
618
115.5 IPS |
|
|
Image Segmentation (SP)
|
100% |
582
9.43 IPS |
|
|
Image Segmentation (HP)
|
100% |
942
15.3 IPS |
|
|
Image Segmentation (Q)
|
99% |
980
15.9 IPS |
|
|
Pose Estimation (SP)
|
100% |
2235
2.61 IPS |
|
|
Pose Estimation (HP)
|
100% |
2075
2.42 IPS |
|
|
Pose Estimation (Q)
|
96% |
1971
2.31 IPS |
|
|
Object Detection (SP)
|
100% |
550
43.6 IPS |
|
|
Object Detection (HP)
|
99% |
960
76.2 IPS |
|
|
Object Detection (Q)
|
92% |
772
61.6 IPS |
|
|
Face Detection (SP)
|
100% |
1280
15.2 IPS |
|
|
Face Detection (HP)
|
100% |
2372
28.2 IPS |
|
|
Face Detection (Q)
|
100% |
1502
17.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
1740
13.4 IPS |
|
|
Depth Estimation (HP)
|
98% |
2673
20.7 IPS |
|
|
Depth Estimation (Q)
|
85% |
2246
17.6 IPS |
|
|
Style Transfer (SP)
|
100% |
4673
6.01 IPS |
|
|
Style Transfer (HP)
|
100% |
7035
9.04 IPS |
|
|
Style Transfer (Q)
|
96% |
6867
8.86 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1254
46.3 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1452
53.6 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
1197
44.2 IPS |
|
|
Text Classification (SP)
|
100% |
284
379.3 IPS |
|
|
Text Classification (HP)
|
100% |
557
743.3 IPS |
|
|
Text Classification (Q)
|
93% |
553
742.3 IPS |
|
|
Machine Translation (SP)
|
100% |
727
12.5 IPS |
|
|
Machine Translation (HP)
|
98% |
1272
22.0 IPS |
|
|
Machine Translation (Q)
|
98% |
1279
22.1 IPS |