| User | voronczoff |
| Upload Date | June 03 2025 05:10 PM |
| Views | 13 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A10X Fusion |
| System Information | |
|---|---|
| Operating System | iOS 17.7.6 |
| Model | iPad Pro (10.5-inch) |
| Model ID | iPad7,3 |
| Motherboard | J207AP |
| CPU Information | |
|---|---|
| Name | Apple A10X Fusion |
| Topology | 1 Processor, 3 Cores |
| Identifier | ARM |
| Base Frequency | 2.34 GHz |
| Cluster 1 | 3 Cores |
| Memory Information | |
|---|---|
| Size | 3.91 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
251
46.7 IPS |
|
|
Image Classification (HP)
|
100% |
220
40.9 IPS |
|
|
Image Classification (Q)
|
96% |
117
21.8 IPS |
|
|
Image Segmentation (SP)
|
100% |
200
3.24 IPS |
|
|
Image Segmentation (HP)
|
100% |
201
3.26 IPS |
|
|
Image Segmentation (Q)
|
99% |
159
2.57 IPS |
|
|
Pose Estimation (SP)
|
100% |
1547
1.80 IPS |
|
|
Pose Estimation (HP)
|
100% |
1413
1.65 IPS |
|
|
Pose Estimation (Q)
|
95% |
948
1.11 IPS |
|
|
Object Detection (SP)
|
100% |
247
19.6 IPS |
|
|
Object Detection (HP)
|
100% |
228
18.1 IPS |
|
|
Object Detection (Q)
|
92% |
136
10.8 IPS |
|
|
Face Detection (SP)
|
100% |
541
6.43 IPS |
|
|
Face Detection (HP)
|
100% |
532
6.33 IPS |
|
|
Face Detection (Q)
|
100% |
212
2.51 IPS |
|
|
Depth Estimation (SP)
|
100% |
695
5.35 IPS |
|
|
Depth Estimation (HP)
|
99% |
632
4.87 IPS |
|
|
Depth Estimation (Q)
|
86% |
406
3.17 IPS |
|
|
Style Transfer (SP)
|
100% |
2241
2.88 IPS |
|
|
Style Transfer (HP)
|
100% |
2133
2.74 IPS |
|
|
Style Transfer (Q)
|
96% |
1452
1.87 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
608
22.5 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
596
22.0 IPS |
|
|
Image Super-Resolution (Q)
|
99% |
285
10.5 IPS |
|
|
Text Classification (SP)
|
100% |
166
221.7 IPS |
|
|
Text Classification (HP)
|
100% |
138
184.2 IPS |
|
|
Text Classification (Q)
|
93% |
139
186.7 IPS |
|
|
Machine Translation (SP)
|
100% |
360
6.21 IPS |
|
|
Machine Translation (HP)
|
100% |
287
4.95 IPS |
|
|
Machine Translation (Q)
|
98% |
286
4.95 IPS |