| User | Moklonus |
| Upload Date | August 18 2024 04:11 PM |
| Views | 26 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | ARM |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| Model | iPad16,3 |
| Model ID | iPad16,3 |
| Motherboard | J717AP |
| CPU Information | |
|---|---|
| Name | ARM |
| Topology | 1 Processor, 9 Cores |
| Identifier | ARM |
| Base Frequency | 4.41 GHz |
| Cluster 1 | 3 Cores |
| Cluster 2 | 6 Cores |
| Memory Information | |
|---|---|
| Size | 7.28 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1953
363.3 IPS |
|
|
Image Classification (HP)
|
100% |
2598
483.2 IPS |
|
|
Image Classification (Q)
|
99% |
2600
484.9 IPS |
|
|
Image Segmentation (SP)
|
100% |
1809
29.3 IPS |
|
|
Image Segmentation (HP)
|
100% |
1747
28.3 IPS |
|
|
Image Segmentation (Q)
|
100% |
1746
28.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
9883
11.5 IPS |
|
|
Pose Estimation (HP)
|
100% |
18757
21.9 IPS |
|
|
Pose Estimation (Q)
|
96% |
16017
18.8 IPS |
|
|
Object Detection (SP)
|
100% |
2083
165.3 IPS |
|
|
Object Detection (HP)
|
97% |
3007
239.4 IPS |
|
|
Object Detection (Q)
|
94% |
2258
180.0 IPS |
|
|
Face Detection (SP)
|
100% |
3596
42.7 IPS |
|
|
Face Detection (HP)
|
100% |
5738
68.2 IPS |
|
|
Face Detection (Q)
|
100% |
3670
43.6 IPS |
|
|
Depth Estimation (SP)
|
100% |
7618
58.7 IPS |
|
|
Depth Estimation (HP)
|
99% |
11116
85.9 IPS |
|
|
Depth Estimation (Q)
|
96% |
5710
44.2 IPS |
|
|
Style Transfer (SP)
|
100% |
23949
30.8 IPS |
|
|
Style Transfer (HP)
|
100% |
35095
45.1 IPS |
|
|
Style Transfer (Q)
|
100% |
35095
45.1 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
5797
214.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
6787
250.6 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
4792
177.5 IPS |
|
|
Text Classification (SP)
|
100% |
3031
4.05 KIPS |
|
|
Text Classification (HP)
|
100% |
5123
6.84 KIPS |
|
|
Text Classification (Q)
|
93% |
5116
6.87 KIPS |
|
|
Machine Translation (SP)
|
100% |
3579
61.7 IPS |
|
|
Machine Translation (HP)
|
98% |
5134
88.7 IPS |
|
|
Machine Translation (Q)
|
98% |
5230
90.4 IPS |