| Upload Date | September 05 2024 05:34 PM |
| Views | 31 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A13 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad (9th generation) |
| Model ID | iPad12,1 |
| Motherboard | J181AP |
| CPU Information | |
|---|---|
| Name | Apple A13 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.66 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.87 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
549
102.0 IPS |
|
|
Image Classification (HP)
|
100% |
2816
523.6 IPS |
|
|
Image Classification (Q)
|
97% |
275
51.3 IPS |
|
|
Image Segmentation (SP)
|
100% |
442
7.17 IPS |
|
|
Image Segmentation (HP)
|
100% |
497
8.06 IPS |
|
|
Image Segmentation (Q)
|
99% |
355
5.76 IPS |
|
|
Pose Estimation (SP)
|
100% |
3323
3.88 IPS |
|
|
Pose Estimation (HP)
|
100% |
28156
32.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
3392
3.98 IPS |
|
|
Object Detection (SP)
|
100% |
572
45.4 IPS |
|
|
Object Detection (HP)
|
100% |
2401
190.4 IPS |
|
|
Object Detection (Q)
|
94% |
291
23.2 IPS |
|
|
Face Detection (SP)
|
100% |
1132
13.4 IPS |
|
|
Face Detection (HP)
|
100% |
6996
83.1 IPS |
|
|
Face Detection (Q)
|
100% |
419
4.98 IPS |
|
|
Depth Estimation (SP)
|
100% |
2039
15.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
23782
183.2 IPS |
|
|
Depth Estimation (Q)
|
86% |
1072
8.37 IPS |
|
|
Style Transfer (SP)
|
100% |
5545
7.13 IPS |
|
|
Style Transfer (HP)
|
100% |
11255
14.5 IPS |
|
|
Style Transfer (Q)
|
96% |
4738
6.11 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
1641
60.6 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
4370
161.4 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
639
23.6 IPS |
|
|
Text Classification (SP)
|
100% |
718
958.4 IPS |
|
|
Text Classification (HP)
|
100% |
432
576.6 IPS |
|
|
Text Classification (Q)
|
93% |
432
579.3 IPS |
|
|
Machine Translation (SP)
|
100% |
788
13.6 IPS |
|
|
Machine Translation (HP)
|
100% |
1017
17.5 IPS |
|
|
Machine Translation (Q)
|
98% |
998
17.2 IPS |