| User | ju83 |
| Upload Date | December 04 2024 06:02 AM |
| Views | 21 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 18.0 |
| Model | iPad Air (3rd generation) |
| Model ID | iPad11,3 |
| Motherboard | J217AP |
| 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 | 2.84 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
270
50.1 IPS |
|
|
Image Classification (HP)
|
100% |
2025
376.7 IPS |
|
|
Image Classification (Q)
|
99% |
170
31.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
256
4.15 IPS |
|
|
Image Segmentation (HP)
|
100% |
389
6.31 IPS |
|
|
Image Segmentation (Q)
|
99% |
201
3.27 IPS |
|
|
Pose Estimation (SP)
|
100% |
1179
1.38 IPS |
|
|
Pose Estimation (HP)
|
100% |
24744
28.9 IPS |
|
|
Pose Estimation (Q)
|
95% |
932
1.09 IPS |
|
|
Object Detection (SP)
|
100% |
290
23.0 IPS |
|
|
Object Detection (HP)
|
100% |
1400
111.0 IPS |
|
|
Object Detection (Q)
|
94% |
202
16.1 IPS |
|
|
Face Detection (SP)
|
100% |
666
7.92 IPS |
|
|
Face Detection (HP)
|
100% |
5229
62.1 IPS |
|
|
Face Detection (Q)
|
0
|
||
|
Depth Estimation (SP)
|
100% |
802
6.18 IPS |
|
|
Depth Estimation (HP)
|
99% |
18528
142.8 IPS |
|
|
Depth Estimation (Q)
|
86% |
509
3.98 IPS |
|
|
Style Transfer (SP)
|
100% |
2078
2.67 IPS |
|
|
Style Transfer (HP)
|
100% |
2040
2.62 IPS |
|
|
Style Transfer (Q)
|
96% |
1724
2.23 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
608
22.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
3526
130.2 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
495
18.3 IPS |
|
|
Text Classification (SP)
|
100% |
282
377.0 IPS |
|
|
Text Classification (HP)
|
100% |
282
376.6 IPS |
|
|
Text Classification (Q)
|
93% |
281
377.6 IPS |
|
|
Machine Translation (SP)
|
100% |
437
7.52 IPS |
|
|
Machine Translation (HP)
|
100% |
340
5.86 IPS |
|
|
Machine Translation (Q)
|
98% |
338
5.84 IPS |