| User | mavica |
| Upload Date | November 01 2024 12:11 PM |
| Views | 10 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.1 |
| Model | iPad (8th generation) |
| Model ID | iPad11,6 |
| Motherboard | J171aAP |
| CPU Information | |
|---|---|
| Name | Apple A12 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 2.49 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 2.88 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
385
71.6 IPS |
|
|
Image Classification (HP)
|
100% |
655
121.8 IPS |
|
|
Image Classification (Q)
|
96% |
534
99.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
406
6.59 IPS |
|
|
Image Segmentation (HP)
|
100% |
718
11.6 IPS |
|
|
Image Segmentation (Q)
|
99% |
762
12.4 IPS |
|
|
Pose Estimation (SP)
|
100% |
1066
1.24 IPS |
|
|
Pose Estimation (HP)
|
100% |
1002
1.17 IPS |
|
|
Pose Estimation (Q)
|
96% |
961
1.13 IPS |
|
|
Object Detection (SP)
|
100% |
360
28.5 IPS |
|
|
Object Detection (HP)
|
99% |
700
55.5 IPS |
|
|
Object Detection (Q)
|
92% |
546
43.6 IPS |
|
|
Face Detection (SP)
|
100% |
900
10.7 IPS |
|
|
Face Detection (HP)
|
100% |
1741
20.7 IPS |
|
|
Face Detection (Q)
|
100% |
1167
13.9 IPS |
|
|
Depth Estimation (SP)
|
100% |
818
6.30 IPS |
|
|
Depth Estimation (HP)
|
98% |
1534
11.9 IPS |
|
|
Depth Estimation (Q)
|
85% |
1363
10.6 IPS |
|
|
Style Transfer (SP)
|
100% |
2084
2.68 IPS |
|
|
Style Transfer (HP)
|
100% |
3602
4.63 IPS |
|
|
Style Transfer (Q)
|
96% |
3461
4.47 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
625
23.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
857
31.7 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
700
25.9 IPS |
|
|
Text Classification (SP)
|
100% |
280
373.7 IPS |
|
|
Text Classification (HP)
|
100% |
561
749.0 IPS |
|
|
Text Classification (Q)
|
93% |
559
750.5 IPS |
|
|
Machine Translation (SP)
|
100% |
556
9.57 IPS |
|
|
Machine Translation (HP)
|
98% |
954
16.5 IPS |
|
|
Machine Translation (Q)
|
98% |
1014
17.5 IPS |