| User | anbG34 |
| Upload Date | August 18 2024 08:04 PM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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 | 3.69 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
854
158.9 IPS |
|
|
Image Classification (HP)
|
100% |
1224
227.5 IPS |
|
|
Image Classification (Q)
|
99% |
1206
224.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
353
5.73 IPS |
|
|
Image Segmentation (HP)
|
100% |
377
6.11 IPS |
|
|
Image Segmentation (Q)
|
100% |
381
6.18 IPS |
|
|
Pose Estimation (SP)
|
100% |
2830
3.30 IPS |
|
|
Pose Estimation (HP)
|
100% |
4028
4.70 IPS |
|
|
Pose Estimation (Q)
|
94% |
1794
2.10 IPS |
|
|
Object Detection (SP)
|
100% |
878
69.6 IPS |
|
|
Object Detection (HP)
|
100% |
1206
95.6 IPS |
|
|
Object Detection (Q)
|
92% |
187
15.0 IPS |
|
|
Face Detection (SP)
|
100% |
3456
41.1 IPS |
|
|
Face Detection (HP)
|
100% |
3966
47.1 IPS |
|
|
Face Detection (Q)
|
100% |
300
3.56 IPS |
|
|
Depth Estimation (SP)
|
100% |
2950
22.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
4183
32.2 IPS |
|
|
Depth Estimation (Q)
|
97% |
4142
32.0 IPS |
|
|
Style Transfer (SP)
|
100% |
7989
10.3 IPS |
|
|
Style Transfer (HP)
|
100% |
9708
12.5 IPS |
|
|
Style Transfer (Q)
|
100% |
9704
12.5 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1437
53.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1897
70.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
394
14.6 IPS |
|
|
Text Classification (SP)
|
100% |
215
287.5 IPS |
|
|
Text Classification (HP)
|
100% |
279
372.7 IPS |
|
|
Text Classification (Q)
|
93% |
281
376.7 IPS |
|
|
Machine Translation (SP)
|
100% |
509
8.76 IPS |
|
|
Machine Translation (HP)
|
100% |
439
7.56 IPS |
|
|
Machine Translation (Q)
|
98% |
415
7.17 IPS |