| User | ju83 |
| Upload Date | August 16 2024 12:33 PM |
| Views | 15 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A12 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.6.1 |
| 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% |
166
30.8 IPS |
|
|
Image Classification (HP)
|
100% |
1625
302.1 IPS |
|
|
Image Classification (Q)
|
99% |
1645
306.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
157
2.55 IPS |
|
|
Image Segmentation (HP)
|
100% |
293
4.75 IPS |
|
|
Image Segmentation (Q)
|
100% |
294
4.77 IPS |
|
|
Pose Estimation (SP)
|
100% |
598
0.70 IPS |
|
|
Pose Estimation (HP)
|
100% |
14511
16.9 IPS |
|
|
Pose Estimation (Q)
|
94% |
507
0.59 IPS |
|
|
Object Detection (SP)
|
100% |
173
13.7 IPS |
|
|
Object Detection (HP)
|
100% |
1084
86.0 IPS |
|
|
Object Detection (Q)
|
94% |
142
11.4 IPS |
|
|
Face Detection (SP)
|
100% |
446
5.30 IPS |
|
|
Face Detection (HP)
|
100% |
4346
51.6 IPS |
|
|
Face Detection (Q)
|
100% |
187
2.22 IPS |
|
|
Depth Estimation (SP)
|
100% |
452
3.49 IPS |
|
|
Depth Estimation (HP)
|
99% |
14231
109.6 IPS |
|
|
Depth Estimation (Q)
|
97% |
14030
108.5 IPS |
|
|
Style Transfer (SP)
|
100% |
1153
1.48 IPS |
|
|
Style Transfer (HP)
|
100% |
1130
1.45 IPS |
|
|
Style Transfer (Q)
|
100% |
1150
1.48 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
329
12.2 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
2530
93.4 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
332
12.3 IPS |
|
|
Text Classification (SP)
|
100% |
165
220.4 IPS |
|
|
Text Classification (HP)
|
100% |
196
261.2 IPS |
|
|
Text Classification (Q)
|
93% |
195
261.9 IPS |
|
|
Machine Translation (SP)
|
100% |
298
5.14 IPS |
|
|
Machine Translation (HP)
|
100% |
234
4.03 IPS |
|
|
Machine Translation (Q)
|
98% |
227
3.92 IPS |