| User | mavica |
| Upload Date | August 23 2024 12:04 PM |
| Views | 6 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | CPU |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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% |
341
63.4 IPS |
|
|
Image Classification (HP)
|
100% |
554
103.0 IPS |
|
|
Image Classification (Q)
|
99% |
538
100.4 IPS |
|
|
Image Segmentation (SP)
|
100% |
336
5.44 IPS |
|
|
Image Segmentation (HP)
|
100% |
451
7.30 IPS |
|
|
Image Segmentation (Q)
|
100% |
463
7.50 IPS |
|
|
Pose Estimation (SP)
|
100% |
1023
1.19 IPS |
|
|
Pose Estimation (HP)
|
100% |
997
1.16 IPS |
|
|
Pose Estimation (Q)
|
96% |
1000
1.17 IPS |
|
|
Object Detection (SP)
|
100% |
314
24.9 IPS |
|
|
Object Detection (HP)
|
99% |
585
46.4 IPS |
|
|
Object Detection (Q)
|
92% |
523
41.7 IPS |
|
|
Face Detection (SP)
|
100% |
741
8.81 IPS |
|
|
Face Detection (HP)
|
100% |
1414
16.8 IPS |
|
|
Face Detection (Q)
|
100% |
1007
12.0 IPS |
|
|
Depth Estimation (SP)
|
100% |
759
5.85 IPS |
|
|
Depth Estimation (HP)
|
99% |
1549
12.0 IPS |
|
|
Depth Estimation (Q)
|
97% |
624
4.83 IPS |
|
|
Style Transfer (SP)
|
100% |
2024
2.60 IPS |
|
|
Style Transfer (HP)
|
100% |
3606
4.64 IPS |
|
|
Style Transfer (Q)
|
100% |
3433
4.41 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
641
23.7 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
865
31.9 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
688
25.5 IPS |
|
|
Text Classification (SP)
|
100% |
250
333.9 IPS |
|
|
Text Classification (HP)
|
100% |
557
744.0 IPS |
|
|
Text Classification (Q)
|
93% |
557
747.3 IPS |
|
|
Machine Translation (SP)
|
100% |
556
9.57 IPS |
|
|
Machine Translation (HP)
|
98% |
894
15.4 IPS |
|
|
Machine Translation (Q)
|
98% |
862
14.9 IPS |