| Upload Date | December 28 2024 08:20 AM |
| Views | 4 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | GPU |
| Device | Apple A12X Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.2 |
| 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% |
834
155.1 IPS |
|
|
Image Classification (HP)
|
100% |
1182
219.8 IPS |
|
|
Image Classification (Q)
|
96% |
155
28.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
360
5.84 IPS |
|
|
Image Segmentation (HP)
|
100% |
374
6.07 IPS |
|
|
Image Segmentation (Q)
|
99% |
222
3.59 IPS |
|
|
Pose Estimation (SP)
|
100% |
2805
3.27 IPS |
|
|
Pose Estimation (HP)
|
100% |
3984
4.65 IPS |
|
|
Pose Estimation (Q)
|
96% |
1693
1.98 IPS |
|
|
Object Detection (SP)
|
100% |
965
76.5 IPS |
|
|
Object Detection (HP)
|
100% |
1256
99.6 IPS |
|
|
Object Detection (Q)
|
92% |
179
14.3 IPS |
|
|
Face Detection (SP)
|
100% |
3413
40.6 IPS |
|
|
Face Detection (HP)
|
100% |
3910
46.5 IPS |
|
|
Face Detection (Q)
|
100% |
295
3.51 IPS |
|
|
Depth Estimation (SP)
|
100% |
2857
22.0 IPS |
|
|
Depth Estimation (HP)
|
99% |
4160
32.0 IPS |
|
|
Depth Estimation (Q)
|
86% |
533
4.16 IPS |
|
|
Style Transfer (SP)
|
100% |
7887
10.1 IPS |
|
|
Style Transfer (HP)
|
100% |
9598
12.3 IPS |
|
|
Style Transfer (Q)
|
96% |
2942
3.80 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1395
51.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
1838
67.9 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
397
14.7 IPS |
|
|
Text Classification (SP)
|
100% |
207
275.6 IPS |
|
|
Text Classification (HP)
|
100% |
258
343.8 IPS |
|
|
Text Classification (Q)
|
93% |
255
342.0 IPS |
|
|
Machine Translation (SP)
|
100% |
303
5.22 IPS |
|
|
Machine Translation (HP)
|
100% |
274
4.72 IPS |
|
|
Machine Translation (Q)
|
98% |
274
4.73 IPS |